Feeding Creatures of Habit

Many Fintech startups compete with banks and other incumbents by offering easy to use and attractive user interfaces. They appeal to users because they offer a modern packaging for processes and at the same time work hard to make these core processes they concentrated on more efficient  (unbundling).

User interfaces are an important aspect for p2p lending marketplaces too. While a very innovative user interface might have contributed in winning the investor, once he registered he not only wants an easy to use user interface he also likes constancy. Sounds paradox?

Fact is, that some p2p lending marketplaces are not that easy to use and offer complex functionality e.g. auctions, secondary markets with discounts and premiums. The investor spends considerable time to learn how to use the functions efficiently. Once he has mastered to efficiently use all the features and reports to achieve good results he will dislike any major changes the marketplace introduces since these force him to “relearn” his way around and render his previously acquired level of experience worthless.

I have experienced this several times on multiple marketplaces. But you don’t have to take my word for it, just look at a forum after a major redesign and you won’t have to search hard to find lots of investors venting their negative opinions rather strongly.

Now knowing that p2p investors are creatures of habit, what could a p2p lending marketplace do to ‘feed’ those? Freezing in standstill is not an option. Even the most conservative investor expects the marketplace to evolve and offer new features.

My suggestions are:

  • The platform should decide early on for a main navigation structure and stick with that. Changes and optimizations should subordinate to that structure and not change this main navigation
  • Development of new features should take wishes of investors into account (do surveys) but not be driven by them entirely
  • Test extensively before releasing. I am repeatedly surprised how many bugs there are in main features after a release (that is they show in main processes and not only in special constellations)
  • Measure, measure, measure. It is sensible to do A/B testing for all larger changes measuring the performance of previously defined KPIs (e.g. bounce rate). If the new version performs worse than the previous version the team should be brave enough to scrap the new developed version even if that means time and cost spent for developing it is lost without an output
  • If URLs change or cease to exist do an automatic redirect to the new URL
  • Even if the marketplace does not encourage the use of tools and automation, it should not ignore the fact that some investors will develop tools and workflows that helps them to speed up their monitoring and investment. The marketplace should consider how the changed impact and process might impact these. The very least that can be done, is to inform investors in advance of an upcoming major change.

Continue reading

Which P2P Lending Marketplace Do You Recommend?

I am often asked “Which p2p lending marketplace do you recommend?“. It is a natural question to ask for people that are familiar with the concept of p2p lending, but have not invested yet.

I feel hesitant to answer it with an outright recommendation for any one marketplace.

Sure I do have my preferred marketplace. Everybody has. But ask 10 different seasoned p2p lending investors and you might get at least 5 different answers. What is right for me, may not feel right for you. There can be no one size fits it all for p2p lending marketplaces. Interestingly as a sidenote investors seem to have less problems to agree why they dislike a platform – and they can also agree on ‘better’ platforms, you just don’t get consensus on the best platform.

What an investor prefers is influenced by his personality and past investment experiences. Investors differ in the expectation they tie to the investment, in risk appetite, in how they perceive and gauge risks. They may prefer a more actively managed investment or a passive investment style. Some enjoy auctions and elements that create competition for others factors like user interface might be a factor that lifts one platform over another.

That such a variety of different models has evolved and still prospers shows that they cater to an audience that is not homogeneous in their needs and wishes. One could argue that there is such a variety because it is a new field and everybody was just implementing ideas and experimenting and there were no role models, but that eventually the models will converge towards a best practise model. And I believe that is and will be happening, but only to a certain degree. Doing business over the internet allows marketplaces to deviate somewhat from the mass market and develop a style that fits a certain clientele easier than it would be for an offline financial offer because the economics of reaching out to and serving this clientele are different.

One entrepreneur recently told me ‘We are different, we just need 10% of the users to like us’ (sry if I rephrased that to much). My answer was ‘Just don’t be to different. Investors are conservative. Why scare 90% of your potential customers away’. I still believe in my answer, because I think it commercially makes sense. However it is minted by my past experience and my perception of the investor behaviour. So I actually want him to succeed in doing things VERY differently and making it as satisfying and enjoyable for those 10% he wants to be the perfect marketplace for.

What do I answer on the question?

At conferences or in other situations without much time, I usually suggest several marketplaces the investor might want to look into and point to my blog for more information.

If there is more time, I usually ask questions to try to find out what the person is looking for, what factors are important for him and what his past investment experience is. Then I tell which marketplaces do well on these factors and might in my opinion be a good match based on what I understood he is looking for. It still feels imperfect and uncomfortable for me sometimes. Maybe it is just a cultural thing, that most people are not comfortable in making recommendations how other people should invest money.

What would be the best answer?

I often think, the straightforward answer is ‘It depends‘. I have never given this answer. Even in situations when I am pressed for a very short answer.

Calculating Yield with XIRR

This is a guest post by German investor Martin R..

P2P Loan Yield

On most p2p platforms (all of mine except Ablrate and Estateguru) principal is paid back monthly during the loan term. The remaining principal decreases every month, the interests do so
accordingly. Inexperienced people are frequently confused by that – a loan over 100 EUR, a term of 5 years and an interest rate of 10% doesn’t yield a profit of 50 EUR, but roughly half of that.
When you think about it for a moment the reason is evident: On average, the capital was only lend for 2.5 years, a part of the debt was already paid back with the first instalment. In exchange, the instalment – as sum of interests and payback – stays the same for the whole running time – minor deviations can occur because of dues of the platform.

Which leads us to a good approximate formula: The obtained interest is about half as high as they would be for a fixed deposit with the same conditions. As already mentioned, the stated yield is still right, though. There are many websites to calculate instalments on the internet you can use to play that through.

Admittedly, such calculations made beforehand become useless if losses or early paybacks occur. And actually, they always occur. How is it possible to stay informed about the current yield in that case?

Mostly, the provider offers calculated ROI calues in the account overview. The shown figures are rarely particularly meaningful, though. Auxmoney for example displays values which
noticeably exceed the interest rate of the lent money – of course that is impossible. There are bookings being conducted wrongly and early paybacks are taken into account as earnings –
that has been happening systematically for years and was never addressed or fixed.

Two ways of calculating yield

In principal, you have to distinguish between already obtained yields ( this is the figure shown by most providers) and the total yield expected at the end of the running time.

The first figure is a good review of the past, but could only be realised if you sold all
your remaining loan parts for their remaining nominal value. Usually, no losses are being considered, not even the already failed repayments. This means the calculated yield is generally too optimistic.
A yield (XIRR, RTI) shown by Bondora or Omaraha of 25% or even more may not be technically wrong, but is not the whole truth either.

Of course, the expected total yield is currently not definite. After all, both future losses and payments due to defaults can significantly affect the yield, meaning the values can only be estimated.
Many refer to a worst-case-scenario when they fully depreciate all credits in defaults and depreciate 50% of all credits that are overdue. But not even that is the whole truth, because usually some of the loans that are current now will fail as well.

The XIRR-function

Thus, you won´t be able to avoid doing your own calculations. Admittedly, it is not possible to do those manually or with help from a calculator for a single loan part with irregular paybacks, let alone a large number of credits. Continue reading

Crowdfunding – Dutch investors – where to go?!

This is a guest post by Dutch lawyer Coen Barneveld Binkhuysen (see full bio at the end of the article)

Crowdfunding is growing exponentially in the Netherlands. Although the Dutch market has not yet reached the astronomical levels of the United States and the United Kingdom, many people have heard about the phenomenon and are intrigued by this potential alternative investment opportunity. While the Dutch market speaks a lot about crowdfunding, it is less familiar with the term p2p-lending (it is commonly available though). As this article covers investments in loans, convertible subordinated loans and equity, I will use the general term crowdfunding instead of p2p-lending.

In the first 6 months of 2015, almost 50 million Euro was raised via crowdfunding, which is double the amount raised in 2014. There are over 80 crowdfunding platforms active in the Netherlands, which makes it difficult for potential investors to gain an overview of the viable available investment opportunities. This article provides a general overview of the most important platforms active in the Dutch market. Furthermore, I will discuss some relevant topics in relation to crowdfunding, such as: diversification options, costs, default risks, cash flow, types of investment and the added value of a properly managed crowdfunding platform.

Overview investment options

In general, crowdfunding platforms in the Netherlands offer the option to invest in loans, subordinated convertible loans and equity (besides donations and the purchase of products). Each of these different investment options has benefits and drawbacks in terms of cash flow, risk and the potential upside can vary significantly:

Loans provide a direct cash flow to the investor as loans are usually repaid in monthly instalments. Loans only have a limited potential upside, maximized at the offered interest rate. Due to the monthly repayments, the risk decreases every month. Most crowdfunding platforms determine the interest rate based on the envisaged risk. As far as I am aware, there are no platforms active in the Netherlands that provide the option to “bid” on loans in auctions.

Convertible subordinated loans (also called convertibles) are considered to entail more risk than normal loans as convertibles are subordinated to (normal) loans and other claims. Investors generally expect a higher return in exchange for a higher risk. Instead of offering a higher interest rate, companies issuing convertibles via crowdfunding offer the option to convert these loans into certificates of shares.[1] The option to convert may be restricted by certain conditions such as (i) a specific period in which conversion must take place and/or (ii) the condition that a sophisticated investor invests at least amount “X” during the term of the loan. For an investor it is important to identify any conversion conditions that may apply. If the loan is not converted into certificates of shares during its term, the investor will receive the principal plus interest payments at the end of the term of the loan. These investments might not be interesting for investors looking for a steady cash flow, but they can be interesting for those who want to have a shot at a serious return.

Equity is normally being offered in the form of certificates of shares (equal to the convertibles described above). Again, investing in equity does not create a steady cash flow for the investor. The terms and conditions related to the certificates of shares may (and normally will) restrict the option to sell them. Therefore, investors are expected to wait for the moment the entire company is being sold to an investor, which can take a long time. Investing in equity might only be interesting for investors looking for long-term investments. Then again, these investments do have the largest potential upside as the investor will profit from every increase in value once the company is being sold.

Balancing risks

Each investor takes, or at least should take, the risk of default into account, especially when investing in high-risk companies such as start-ups. Business cases of start-ups have not yet been properly tested and most do not, or hardly have, any financial buffers. Should the financed company go bankrupt, practice shows that only in rare cases (only part of) the loan can be recovered. Normally, preferred creditors such as banks and the tax authorities will receive the benefit of all assets left in the company and there is nothing left for others. Some platforms try to reduce the risk by requesting a personal guarantee of the entrepreneur, but this is of little use if the person does not have any assets.

The actual difference between investments in loans, convertibles and equity from a risk perspective is small. Investors having certificates of shares have a larger potential upside than the holders of loans. One could say that investors almost bear the same risk, but with different potential upsides. In my opinion the most important reasons to choose for normal loans are the fixed term and monthly repayments. If you are not in a hurry to make a profit and are going for the highest potential return, convertibles and equity might be a more interesting option.

Overview largest platforms in the Netherlands

After selecting the preferred investment instrument, it is important to select one or more of the available crowdfunding platforms. Without aiming to be complete, I list the largest and most active platforms active in the Netherlands below:

nl-geldvoorelkaarGeldvoorelkaar.nl is the national market leader and funded over 825 projects, with a total sum of over 66,000,000 Euro. The platform focusses on p2p-lending and only provides investors the opportunity to invest in loans. Interest rates range from 4% to 9% depending on the risk score determined by Geldvoorelkaar.nl. All loans are being repaid in monthly instalments as of the first month. By investing in projects via this platform, it is fairly easy to generate a decent cash flow. Up to now, 3.5% of my investments on the platform have defaulted. As the principal of one of the defaulted projects was almost fully paid back, my average ROI still accounts for about 6.5% per year. The other defaulted project was probably a case of bankruptcy fraud, which I expect to happen more often in the future. The platform opens several dozen new projects every week, which creates sufficient opportunities to diversify your portfolio and reinvest your money. An investor must pay a fee equal to 0.3% * loan duration (in years) * invested amount (which amount will be refunded if the project defaults).

nl-oneplanetcrowdOneplanetcrowd claims to be Europe’s leading sustainable crowdfunding platform. Since launching in 2012 it raised over € 6 million in funding for more than 100 projects. Oneplanetcrowd operates in Germany and the Netherlands and is planning to open in other European countries soon. It provides investors the option to invest in loans and convertibles (apart from donations and presale options) and offers some of the most interesting investment opportunities, such as Snappcar and Wakawaka Power. Various projects offer the opportunity to co-invest with sophisticated venture capital firms as these firms invest simultaneously with the crowdfunding campaign. In my opinion, this is a huge advantage for investors as VCs tend to do a thorough due diligence before choosing to invest. The platform only allows companies with a sustainable philosophy to start a campaign on the platform. Their goal is to provide high quality investments with a decent return to investors. Although this is a good niche market, the strategy makes diversification opportunities fairly difficult. Investors do not pay a fee on Oneplanetcrowd.

nl-other

KapitaalOpMaat and Collin Crowdfund are some of the main competitors of Geldvoorelkaar.nl as these platforms focus solely on loans with loan periods ranging from 6 up to 120 months and interest rates of 5.5% up to 9% depending on the calculated risk. Almost 6.5 million Euro and 13 million Euro have been funded via these platforms, respectively. Investors on KapitaalOpMaat pay a one-time transaction fee of 0.9% and a yearly fee of 0.85% on Collin Crowdfunding. Both platforms provide discounts to investors investing more than certain thresholds.

Bondora is a European platform offering the opportunity to invest in loans on a European level. Although this is by far the most sophisticated (international) platform available to Dutch investors, its presence is fairly unknown to most Dutch investors. Already more than 35 million Euro has been financed via Bondora. Investors are allowed to choose their own investments on the primary market, but most loans are filled in advance by a bot. Therefore, it will be necessary to invest automatically via the provided bot in order to obtain sufficient loans. This enables the investor to invest in literally thousands of loans differing in purpose, country and risk. All loans are repaid in monthly instalments on a virtual account. Bondora also offers the option to purchase/sell investments to other investors on its secondary market (with a premium/discount) against a fee of 1.5%. Investors do not pay any fees on the primary market. Although Bondora claims an average ROI of 18.75%, many investors complain about the large number of defaults. As the minimum investment is only 5 Euro, the threshold is low.

Symbid is one of the established Dutch crowdfunding platforms and focuses on equity (certificates of shares) and loans. Although Symbid seems to suggest that already more than 300 million Euro has been invested via their crowdfunding platform, the actual amount funded by the crowd is closer to 6 million Euro. One of the advantages of Symbid is that it offers the option to sell your equity to other investors on the platform. Continue reading

Bondora Investments Using Decision Trees – Review of Progress – Part 6

This is part 5 of a series of guest posts by British Bondora p2p lending investor ‘ParisinGOC’. Please read part 1, part 2,  part 3 and part 4 and part 5 first.

Plan Your Change And Change Your Plan!

As stated in the previous article (see part 1-3) and revealed in the graphs of performance, I started using the Decision Trees in response to the rapid rise in defaults in my portfolio. Except for very small numbers of “opportunistic” purchases, I have maintained a strict discipline on purchase in order to ensure that my progress could be monitored and assessed. As my confidence has grown, I have modified this discipline to take advantage of the Bondora environment to achieve the demanding personal goals I had set myself when I first started. These included only purchasing Loan parts that should accrue 50% interest over the forecast life of the loan – i.e. should turn 5 Euro into 7.5 Euro over the original loan period.

Since early June, I have modified this discipline further and now purchase loans that, whilst still meeting my overarching rule of looking for 5% to 7% historical default levels, do not have a high enough interest rate to meet my earlier profitability goal. I intend to try and sell these loan parts on the Secondary Market with a short-term profit goal, after Purchase/Sale costs.

This further leg of my overall strategy is still in its infancy, but the results from my use of Decision Trees in my initial selection of Loan Applications suggest I am buying the best performing loans available. This means that should other investors not share this view, I will at least be left with Loan Parts that will perform well for me for the time I hold them.

Given the latest changes at Bondora mentioned earlier, if I can only acquire “good” (as defined by the Decision Tree analysis) from the Secondary Market, it may be that this buy-to-sell tactic may not be possible into the future.

Tree development

Tree Analysis

In the previous article (see part 1-3) on the construction of the Decision Trees, I explained how I had made adjustments to the overall analysis process to give more weight to factors such as “Total Income” in the actual Decision Tree analysis. I have kept the included data under constant Review and have added a few further fields to the analysis process, in particular the field showing the “Total Monthly Income/ New Repayment”. As stated in the first article, this needed to be modified from an infinitely variable value into 20 ranges, each of equal numbers of samples.

I mention this particular field as, since January 2015, it appears as an important feature in both the Estonia and Finland Trees and continues to appear more often in these Trees.

Volume and confidence

It is a fact that Estonia has been the largest market for Bondora from its days as Isepankur. In simple volume terms, the data I use (from 1/1/2013) shows that Estonia accounts for c.50% of the total loans, with Finland and Spain making up about 25% each. Slovakia is simply no longer mentioned in polite, Bondora society, so I will pretend it never happened!

Whilst it is true that Estonia has a lower historical default rate, in the dataset that I use, defaults do occur and are presently running at around 11.986% (1009 out of 8418), compared with exactly 18% (576 out of 3200) for Finland and 27.059% (1022 out of 3777) for Spain.

The above figures carry several implications as follows:

The Estonian Tree is fairly static with few changes at the highest levels. Estonian Loans within Bondora bring with them a richness in the data, by which I mean that the original Credit Scores are well represented across the Loan Applications compared to Finland and Spain, which are almost entirely populated with examples with a Credit Score of “1000”. What this means for Estonia is that the Decision Tree neatly shows that the Bondora Credit Score is relatively accurate, with higher numbers of defaults at lower Credit Scores. Thus it is that the historical record shows that Loan Applications with a Credit Score of “1000” (the highest and most sought after) make for good hunting when searching for segments having a default rate of less than 5%. Indeed, it is not uncommon for the Decision Trees to reveal segments of 50+ examples with NO defaults over the last 2.5 years.
Finland and Spain however, with very few historical Loan Applications with a Credit Score of anything other than “1000” combined with a default rate 50% and over 100% higher respectively than Estonia AND volumes less than half that of Estonia, provide pitifully few obvious segments with a sub-5% default rate AND sufficient numbers of examples to support anything like the confidence levels of Estonia.

I believe that the lack of richness in the Finnish and Spanish data is revealed in the overall structure of the different Trees.

Estonia

The top-most branch in the Estonian Tree is based upon the Employment Status of Estonian Applicants. This represents 5 different values: Full Employment (c.90%), Entrepeneur (c.4%), Self-Employed, Retired and, finally, Partially Employed (these last at c.2%).

The Credit Score generally appears at the 2nd, 3rd or 4th level below this and, as stated above, provides a firm “fault line” between >5% and <5% default rates in most of the segmentation below these levels.
As noted earlier, for those in Full Employment initially Income and latterly the ratio of cost to income (which I refer to subsequently as “Affordability”) is the next most significant differentiator followed by Credit Score with the paths exhibiting differing significant data elements somewhat below this level.

A strange (in my eyes) feature of what I call “Affordability” that appears in the Estonian Tree for those in Full Employment is an apparent truth that the more someone can afford to cover the cost of the loan, the less likely they actually do so and the more likely it is that default will occur! 17.333% (65 out of 375) of those in Full Employment who appear to be most able to afford their loans go on to default whereas only 6.54% (24 out of 367) of those in Full Employment showing the lowest affordability have defaulted. So it seems that, in Estonia, the higher the ability to pay, the less likely this is to occur!

Finland

The lack of richness in the Credit Scores provided by Bondora for Finnish (and Spanish) Loan Applicants is revealed, as the Credit Score is the primary determinant at the top level. This is, however an almost totally useless determinant as just over 98% (just under 98% for Spain) of all Finnish Loan Applications carry a Credit Score of “1000”. Below this level, Employment Status is the prime determinant, as in Estonia, but there any resemblance ends as lacking the Credit Score and with lower overall volumes and there is no common thread to the analysis.

Latterly the ratio of cost to income (what I have termed “Affordability”) has crept in at lower levels but there is no pattern to be discerned and the Tree has not settled down to any pattern at the lower levels with changes occurring at all iterations.

Such are the problems with low volumes and high default rates that I have changed the parameters for the Decision Trees for Finland and Spain to force the analysis to work with higher volumes in the nodes and leafs (end points) in an attempt to increase confidence levels. This has the unfortunate side effect of there being few leafs with a sub-5% default rate, the notable exception being a leaf of 23 examples with a 0% default rate.

Spain

As noted above, Spain shares with Finland the feature of Credit Score and Employment Status being the top 2 levels but for Spanish Loan Applicants in Full Employment, the number of Dependants appears to be the most important factor and has remained so for over 6 months of analysis. This data element does appear occasionally in both other trees, but only at much lower levels.

Other than this notable difference, the overriding feature of the Spanish Decision Tree is the lack of leafs showing a sub-5% default rate. Even where sub-5% default rates can be found, there are so few examples in the set with little in the way of trend or discernable pattern to support confidence at any instinctive level.

The best sub-5% default rate is a leaf of 21 examples, being 4.75%, for fully employed, divorced people with 1 dependant living in Pre-Furnished property! All other leafs with a sub-5% default rate are based on less than 10 examples. Many are only single examples.

A competent statistician (which I am not!) may be able to pry some hidden gems from this Tree, but I fear not.

Conclusion

The Decision Trees themselves, whilst changing over time, now appear to have settled down and changes that occur do so at finer levels of granularity with only occasional changes in the overall structure of any particular tree.

The numbers of samples (the complete Bondora dataset) entering the process have now reached the level where the Trees for Finland and Spain required modification of the actual Decision Tree analysis (known as an “ID3” tree) to increase the sample sizes at the lowest level. This has increased my confidence in the output even though the levels of default are so high that identifying sub-5% default levels leave me rejecting many more Loan Applications than I actually invest in.

My initial, restricted purchasing at the start of my new strategy has opened out over the course of period under review. After an initial period where my cash reserves grew to over 25% of my initial investment at Bondora, I am now confidently pursuing new avenues of activity with a view to maximising my returns within the opportunities suggested by the Decision Tree analysis.

This success in using manual selection of investment opportunities comes in the face of constant change at Bondora, change that is trying to move the investment process towards a passive, easy-to-use activity – an understandable business logic.

I take some comfort that my total efforts to date (which include aggressive management of non-performing loans) appear to be returning better than average results. In conclusion, I believe that my change from instinct- to numbers-lead investing has improved my portfolio performance when measured by this admittedly coarse scale of default level. Furthermore, this process has allowed me to start to take a wider view of the opportunities available on the Bondora platform and I hope to be steering my returns back to the levels that initially drew me to this platform.
In terms of the performance over the past 9 months, I experience severely reduced default levels going forward compared to those that triggered my realisation that a new investment strategy had to be formulated. I am now seeing levels similar to those last observed almost 2 years ago, on purchasing volumes approximately double those from that time. I will be the first to admit that the loans purchased over the last 9 months have yet to “mature” to the level of those from nearly 2 years ago, but I have a renewed confidence in the future performance of my portfolio at Bondora.

P2P-Banking.com thanks the author for sharing his experiences and strategy in detail.

Back in March an investor from Luxembourgh wrote an article sharing his experiences in applying machine learning to peer-to-peer lending at Bondora.

Bondora Investments Using Decision Trees – Review of Progress – Part 5

This is part 5 of a series of guest posts by British Bondora p2p lending investor ‘ParisinGOC’. Please read part 1, part 2,  part 3 and part 4 first.

The Management of Change

As mentioned in my earlier article on the construction of the decision Trees, my responsibilities when employed (yes, dear reader, I am now retired) included the successful proposal to create new teams to conduct Data Mining and produce and disseminate Metrics relating to the research activities. As on many other occasions, I was then charged with making my assertions real by staffing and then running said teams to realise the benefits I had stated should arise.

As part of my (rapid) learning in these activities, I came to understand the need to maintain processes until solid analysis could isolate and support changes. So in this review period, for those elements under my control, I have maintained certain actions within set parameters until I felt I could justify a change and then have maintained that changed process until the next time the data supported a further change.

Changes I Controlled

Given that my need to change my selection process was as a direct of seeing my money rapidly disappear (!) I limited my ongoing expenditure to the minimum purchase (5 Euros) allowed by Bondora and only made 1 purchase per selected Loan Application.

This continued throughout October 2014, when I felt that the downward trend in parts falling behind with payments was established and likely to continue. From the beginning of November 2014 onwards I increased the number of parts of any single loan application I would buy to 2, still of 5 Euros each. Note that for some application types with, for example, a higher (between 5% to 7%) indicated historical failure rate, or a very high (above 45%) interest rate; I still limited my purchasing to 1 part of 5 Euros.

This Purchasing policy remained in place until the beginning of April 2015 when my increasing confidence in the selection process, my increasing cash reserve and other factors described below, meant I felt able to increase the value of purchases (to include 10 Euro parts if I felt an application was sufficiently strong) and increased the number parts purchased of any particular loan. This latter element in particular allowed me to take advantage of events outside of my control that offered opportunities that had not previously existed, explained later in this article.

Errors in my Process
In the period October 2014 to the end of the year, I was updating the Trees twice a month. There was no detailed timetable, but the Trees did exhibit a greater degree of change in this time than was later the case. It was during the first update in December, week 51 of 2014, I noticed that the previous Tree had been built using corrupted data. It was only later in the review period that I noticed that this period – from weeks 48 to 50 inclusive – exhibited the last “spike” in defaults.

From the next update onwards (31st December 2014) I implemented a more rigorous update procedure and restricted the updates to 1 at the end of each month. I felt that this may enable changes in the Tree Structures to be more visible and so attract my attention to these changes and validate the process that had generate them, thus avoiding process errors. The fact that the datasets provided by Bondora were subject change without notice (and did so often) was an additional factor in the decision to have fewer, more rigorous build events.

I worried that fewer updates to the Trees would lead to out-of-date trees and more In Debt and Defaulting loan parts, but this has not become apparent either in daily use or this review process.
I have noticed that the Decision Trees are not static and do change over time. Sometimes – rarely – these changes occur at a high level and are very noticeable. However, the Trees have changed in a subtle way at lower, more compartmentalised levels. This is discussed later in this article.

Changes I could not Control

Whilst I have tried to maintain a tight control over my activity since starting to use the Decision Trees to guide my loan selection, there is the overall Bondora environment over which I have no control. As noted in the previous article (see part 1-3), Bondora is a dynamic environment and changes, whilst usually signalled in advance, cannot usually be planned for and just have to be accommodated when the reality of the change becomes apparent. Where possible I have noted the changes that have occurred. As part of this review, I have gone back over the last 9 months activity to try and relate these changes and how I believe they have, or may have, affected my results.

Portfolio Manager
The Portfolio Manager in place up to the end of 2014 was an automated, parameter-driven mechanism to allow investors to automatically invest in loans that meet the criteria set by the investor. From the start of 2015, Bondora made major changes to the Portfolio Manager, preceded by allocating a “Risk Segment” (running from low to high risk) to each Loan Application.

Whilst a Loan Application retained the previous Credit Score and associated Credit Group (essentially an income-related grading), these no longer played a part in the new Portfolio Manager, which no longer allowed Loan Selection by any criteria other than the new “Risk Segment”. Probably the most contentious element of the new Portfolio Manager was the loss of selection by Country. The use of Country was a critical element in the previous automated selection process for most ( if not all) investors, and its loss was not well received on the official forum.

In terms of my process of Decision Tree analysis, this changed nothing. All the previous data was still present and some new data was added about the New Risk Segment and the process associated with it. I have considered adding the new Risk Segment data to the Decision Tree analysis, but decided against this primarily as its introduction, occurring as it did some 3 months into my experiment, had the potential to dramatically alter the structure of the Decision Trees, creating a possible disconnect at this point.

A secondary reason in my decision was the fact that this data was itself the result of an analysis conducted by Bondora and for which there is no detailed discussion or publication showing how it has been arrived at. Whilst I am not surprised at the decision not to publish what is, after all, company confidential data, the output – a legend consisting of a 1- or 2-letter classification – is not an independently verifiable fact, it is merely the output from an analysis and shares this feature with my own Decision Trees.

The major difference between this and the Decision Tree output I have is the context that is provided by a full Decision Tree to those who wish to use it. IMHO, the discerning viewer can decide from the context of a complete Decision Tree whether the end point of a particular branching of the tree indeed describes a trend or is just a convenient mathematical activity that segregates the data, but reveals no trend. I offer the snapshot of Self Employment from the Decision Tree for Estonia as an example of this added value.

Decision Tree View Estonia Bondora

 

To me, the bigger picture describes a trend suggesting that the longer the applicant has been in the same employment, the less likely a default will occur. It also shows that the Decision Tree has found that those in the same employment for over 5 years can be further segregated by age, with all defaults occurring in a single age range (45 to 51). Furthermore, the sample size of the >5 years employment is 51 and the defaults, which all occur in the noted age group, amount to just 2 examples – a 4% default rate on the set of 51 as a whole. Is this further segregation a guide to investment or just a “Clump” in a larger data set? In the words of the immortal Clint Eastwood “You’ve gotta ask yourself one question: “Do I feel lucky?Well, do ya, punk?.

Application Process

In last half of February 2015, Bondora introduced changes to the application process designed to allow applications to be assessed by Investors before all data had been collected and, where applicable, validated.

This had no immediate effect on the Decision Tree analysis, but did require minor amendments to the process. Many applications were taking up to 5 or even 6 attempts before they became fully acceptable and finally funded. Many of these rejections took place after funding was in place. They were then cancelled and re-submitted with updated data. It was important that such applications did not get counted as “Previous Applications”. This field does appear in some lower levels in a Decision Tree and therefore new data cleaning activities (explained in the previous article) had to be introduced into the process.

Server Capacity Issues at Bondora

Around the 2nd week in March, 2015, the servers at Bondora ran into capacity issues. This affected both the ability of the applicant to apply for loans and for investors to lend.

Aggregated effect of Bondora changes

Concurrent with the introduction of the changed application process and the server capacity problems, it is apparent from a chart provided by Peerlan that the new Portfolio Manager’s ability to fund loans collapsed, effectively to zero.

Portfolio Manager Funding from Peerlan - 2015-06-23 snapshot

When Bondora fixed their capacity problems, the mix of Loan Applications becoming available to manual investors had changed dramatically. Whilst this had no effect on the use of Decision Trees to select loans, it meant that many more loans became available to manual bidders. Many of these loans were Estonian, historically considered to be of higher quality.

This availability of more loans of potentially higher quality is reflected in my activity by the highest level of loan part purchases seen since the start of my use of Decision Trees. This higher number of purchases occurred even with the restrictions I had placed on myself regarding the level of purchases per Loan Application, mentioned earlier.

As I write this review, the new Portfolio Manager process has again changed, this time to run more often, with a target of running effectively all the time. This new process appears to have a dramatic effect during the 16th July, reducing opportunities for manual bidding on new Loan Applications essentially to zero, as the new Portfolio Manager process swept up all new listings.

New Loan Applications have appeared again the next day and a close reading of the Bondora “Guide to Investing” FAQ suggests that Loans that fail to be filled immediately should appear out of the back of the new process and become available to manual investing and this appears to be the case. This occurrence and the availability of loans on the Secondary Market (at a premium in most cases), leaves me feeling that my work to date has not been in vain. Time will tell!

Flip forward to the final part 6.

Bondora Investments Using Decision Trees – Review of Progress – Part 4

This is part 4 of a series of guest posts by British Bondora p2p lending investor ‘ParisinGOC’. In part 1, part 2 and part 3 published in December 2014 you could read how he used the data to built decision trees to identify lending opportunities. Now you can read how that strategy worked out.

Introduction

In August 2014, I realised my portfolio of P2P loans at Bondora was not performing as I would wish. There was an urgent need to change the way I selected loans in which to invest the money I had at my disposal. My search for a better way of selecting loans lead me to use Decision Trees to analyse the loan data available from Bondora using “RapidMiner” – software available to download for free.

It is now over 6 months since I described my original work to construct the Trees. This follow-up article chronicles what I believe is the success of my efforts to date whilst also describing the multiple factors, both within and beyond my control, that mean that, whilst I feel very comfortable with the progress made to date, others may feel that I have just been lucky!

The journey since I created my first Decision Tree and started to make purchasing decisions based almost totally on their outputs has been one of constant change. Detailing the changes to elements over which I have no control has shown me how they contribute to what I believe is success as much as my own efforts to improve the selection processes. Describing the change in the Decision Trees as well as their use in the dynamic Bondora environment has left me feeling that, without constant monitoring and review of both the process of creating the Trees as well as their use, it may still be very easy to snatch defeat from the jaws of victory.

Key to ensuring the veracity of my protestations of success has been the maintenance of a consistent approach to my selection and lending process. To this end, I will describe those changes to my process that I can control and explain how and why such changes have taken place. In short, I have maintained a restricted buying policy, investing only the minimum amount (5 Euros) at any one time and, latterly, only buying a maximum of 2 loan parts (of 5 Euros each) in any one loan, depending on the outputs from the Decision Trees and my own mood at the moment of purchase.
I realise that this last phrase is not at all scientific, but the fact that my Portfolio of c.12000 Euros was not performing as expected was for me, a non-trivial affair and some emotional response has to be accommodated.

I have already stated that I believe my efforts have been successful. This is based on the fact that the rate of default (Once a loan principal has been overdue for 60+ days, it is labelled as “defaulted” – Bondora FAQ) in my portfolio has returned to historical, pre-2014 levels. Up to this time, even though I had come to realise that I needed to actively manage my portfolio, my selection of loans was done almost entirely using the “Portfolio Manager” – an automated, parameter-driven purchasing function provided by Bondora and supplemented by instinctual analysis of the descriptions of the Loan Applications available to invest in.

Simple Chart - Held Loans and Defaults

 

Looking at the simple chart of Held Parts/Defaults, the number of defaults in held loans rose significantly over the summer of 2014, coinciding with a big increase in both the number and value of investments on my part. Referring to the same chart, it can be seen that, even though the number of investments remains close to summer 2014 levels, my defaults have fallen to the numbers experienced earlier, at much lower volumes.

With my new-found confidence that I have a process for selection and management that appears to be sound, I have started to increase the volume of Loan Parts purchased so that the value is now approaching Summer 2014 levels of investment.

Progress to date

Graphical representation of Progress

I will use a more detailed graph showing the volume of Loan Parts purchased, those subsequently sold, those “Overdue” and those in default (still held by me as well as sold) to hopefully illustrate the performance of my selection and management processes. Continue reading

One Year Invested in Zencap

This is a guest post by German investor Martin R.. The article was written in April.

These days, Zencap celebrates its first anniversary. I’ve been involved right from the beginning and invested the full 10k€ you can invest without having a premium account.

Zencap – my characteristics

Zencap offers investment in corporate loans. You invest 100 EUR in one loan. The total loan is usually between some 10,000 EUR and approximately 200,000€. There are different scoring classes essentially determining the interest rates which are usually located between 5% and a little over 10%. The loan term ranges from 3 months up to 5 years, the main focus being 3 years. As the loans are instalment loans, you will usually have half of your investment plus interests available after 18 months. The nominal interest rates are decreased by 1% through fees for the investor. The loan listings are presented with a short description and have differently detailed documents attached. Some projects have personal sureties.

My experiences

are mixed. I’m rather satisfied with a yield of about 5.7% and no payment delays up to now. The payout takes place promptly after the scheduled payment at the 15th of each month. The bidding amounts are straightforwardly drawn through direct debit, however, the period between bidding and drawdown drag on very long from time to time (debiting is just before the first paying out, though). Now and then there are special promotions which increase the yield (see below). Continue reading

How I Explored P2P Lending – My Review Part II

This is part II of a guest post by British investor ‘GSV3Miac’. Read part I first.

Most of my concerns about P2P lending revolve around its relative immaturity. Even ZOPA, the oldest in the UK, has only been around 10 year or so, and have changed ‘just about everything’ at least twice. Funding Circle (“FC”)have 3-4 years history, but there have been no two years where the business has actually been stable (maximum loan sizes, loan terms, Institutional participation, etc. have all changed pretty much continually over the period I’ve been investing). How well the companies, and their borrowers, would survive a real recession, can only be guessed at.

What do I actually invest in? Well practically anything if the rate looks good. My ‘core holding’ is in RS, but there is nearly as much spread across the P2B platforms. For extra P2P related risk (and maybe reward) I also signed up to invest in the Assetz and Commuter Club capital raises (via SEEDRS). With EIS investments some of the money at risk is renated tax, which you had a 100% certainty of losing to the government anyway.

I do not plan to hold most of my investments (particularly in FC) for the full 5 years. After a few months the financial data is well out of date (much of it is already out of date when the loan is approved!) and unless you want to spend time checking how the company is doing, it is easier to sell the loans on and start anew.

Similarly if rates start to move dramatically, it’s time to ‘flip’ or ‘churn’ .. selling a 7% loan part when rates move to 9% is possible, but might sting a bit. Selling a 7% loan part when rates have moved to 14% is going to hurt a lot, or might be completely impossible. If rates move the other way, selling a 7% loan part when average rates are 6% is not only easy, it may be profitable (assuming the platform allows marking up). You might wind up with un-invested funds, but as someone succinctly put it on the P2P forum, ‘un-invested is a lot less painful than lost’.

The future looks equally interesting .. we are promised P2P investments within an ISA (do NOT hold your breath, this seems to be moving at a glacial pace so far), which could result in a ‘wall of money’ arriving on the scene. We are promised P2P losses to be tax deductible (against income, rather than capital gains), which has an impact on the worth of a protection fund. We will inevitably see some new entrants appear as the P2P area grows and become more attractive (Hargreaves Lansdown, a very large fund management player, has already indicated they might get involved, I believe). We will equally inevitably see some more of the current players merge or vanish, and many of the loans default.

As I may have mentioned a couple of times, nothing has been very stable so far .. most of the platforms are still ‘feeling their way’ with immature software (this is polite-speak for ‘bugs’), and business models/systems which are still evolving. The basic P2P premise of connecting people with money with people who want it, without too much activity in the middle, does not appear to scale too well when the number of each side get big (a million people bidding to fund a thousand loans each day is not something to contemplate lightly). Platforms need to grow to survive and they need to grow in balance – if they double the number of lenders, they need twice as many willing borrowers, and vice versa .. Asymmetrical growth just annoys whoever is on the surplus side, distorts the rates, and results in no growth at all – you need both a lender and a borrower to have any business. It is obvious, but very hard to manage. Continue reading

How I Explored P2P Lending – My Review Part I

This is part I of a guest post by British investor ‘GSV3Miac’.

About the author.. I spent 25 or so years in software engineering, programming everything from IBM mainframes to microchips in early Hotpoint washing machines. I must have been halfway competent (or not) since I wound up managing a software development group, a large IBM computer centre, workstations of networks and PCs. When my (American owned) factory shut down I spent the last year (in between managing the closure) retraining as an IFA. I qualified, but I never actually practised – I took my redundancy / pension and headed for the hills (of Shropshire). That was a while ago, so don’t expect me to know chapter and verse on the latest tax wrinkles! *grin*

How did I get into P2P (misnamed .. it’s largely P2B these days .. much of is headed for B2B!) lending? Blame my mother .. she died, and left me a sum of money which was not expected, and not really critical to my future. Having no children (there being, IMO, no people shortage on the planet) it is probably all headed for charities one day, so I thought I might as well have some fun with it. Before I did that, I had, of course, gone through the approved checklist .. i.e.

‘Emergency’ easy access cash account(s) .. tick.

Pay off the mortgage .. tick.

ISA(s) .. tick

Pension Provisions .. tick

Stock market investments / bonds / shares / funds ..tick

OK, anything left can be risked a bit. (I accept that stocks and shares and even cash has =some= risk attached, but now we are looking at ‘high wire with no net’ type options .. VCTs, EIS schemes, and yep .. P2P lending). If you want to plan for ultimate disaster (Ebola pandemic, nuclear war and global financial meltdown) then probably investing in long dated canned food, and an underground shelter on an island upwind from everywhere, is your best bet. More modest (and likely) risks can be mitigated by spreading your investments around a lot, and by being conservative in your assumptions of what you might get back.

I started my P2P journey (in 2013) with Funding Circle (henceforth ‘FC’) and ZOPA, both of which I had heard about from a friend, and I dipped my toes in rather gingerly at first. ZOPA had been going for some time, and I probably missed their best years (when you could decide who to lend to, and later when you could at least still decide at what rate you’d lend). ZOPA had just introduced their ‘safeguarded’ lending, and started fixing the rates, so even their name (‘Zone Of Possible Agreement’) no longer made sense. I stopped lending with them after less than 6 months .. the rates were just not attractive (and unpredictably so). On the plus side, the exit from ZOPA was fairly cheap and painless.

As an alternative to ZOPA I went to look at Ratesetter (RS), which still lets you set the rate(s) you are willing to lend at over 1,3 or 5 years (or monthly). No control over who gets it, but at least some control over what they pay; and (like modern ZOPA) there is a provision fund which should hopefully protect you from bad debts. Exit from RS can be quite expensive though, so best to lend for no longer than you are sure you can do without the money for. Basically they charge you the difference between the rate you would have got for the actual period you lent for, and the rate you got by lending for a longer period. I still like them, for simplicity with just enough control to make it interesting, and I lend / recycle in the 3 and 5 year markets depending on the rates at the time (typically I expect at least an extra 1% for signing up for the extra 2 years). Continue reading