Introducing CreditWiseInvest: A free ML app to help you pick the best loan pool on a risk-reward basis
Problem Statement:
Peer-to-peer lending marketplaces such as LendingClub and Prosper Marketplace operate on a model where they act as intermediaries connecting investors with borrowers. These platforms charge a broker's fee for facilitating these transactions and are motivated to increase the total number of transactions occurring on their platforms.
However, the current approach to credit risk assessment on these platforms relies on off-the-shelf models that categorize borrowers into grouped buckets based on credit scores. While this approach may be convenient, it fails to account for the uniqueness of each loan and the extensive data available from borrowers. Assessing credit risk on a more granular and continuous basis, rather than discrete grouped buckets, presents an opportunity to enhance the efficiency and accuracy of risk assessment in peer-to-peer lending.
Understanding and managing credit risk is crucial for investors in peer-to-peer lending and bond markets. Institutions, like large banks, dedicate resources to analyze borrower data, aiming to enhance risk assessments and investment decisions.
The primary risk investors face is borrower default, where borrowers fail to make required payments, resulting in potential loss of principal and interest. To assess potential returns, investors consider loan terms and borrower profiles.
For everyday investors seeking simplicity and effectiveness, a user-friendly tool is needed. This tool should offer improved risk assessment compared to off-the-shelf advisors, empowering investors to make informed decisions and potentially outperform the market.
Solution: CreditWiseInvest
CreditWiseInvest helps individual investors augment their portfolio by intelligently allocating funds to Peer-to-Peer Lending Marketplaces using machine learning trained on LendingClub.com historical loan data to assess risk and predict return.
CreditWiseInvest recommends the best loans to invest in given a user’s available funds, maximum risk tolerance, and minimum desired annualized return. There are plenty of institutions that are thought leaders in utilizing modern, alternative datasets to assess credit risk and predict investment potential, but I’ve simplified the problem into 2 key models:
(1) scoring risk by predicting the probability that a loan defaults, and
(2) predicting annualized returns.
Important Terms & Concepts:
Peer-to-Peer Lending (also known as P2P or Crowdlending):
Peer-to-Peer Lending (P2P): Online platforms connecting lenders directly with borrowers, offering higher returns for lenders and lower interest rates for borrowers compared to traditional banks.
Artificial Neural Network (ANN): A computational learning system that uses a network of functions to translate data inputs into desired outputs. Inspired by the functioning of neurons in the human brain, ANN can understand and process inputs from various sources.
Random Forest Model: An ensemble learning method that constructs multiple decision trees during training and outputs the mode of classes or mean prediction of individual trees. It is used for classification, regression, and other tasks, providing robust and accurate predictions.
Probability of Default: An estimate of the likelihood that a borrower will fail to meet its debt obligations, indicating the risk associated with lending to that borrower.
Annualized Return: Returns over a period scaled down to a 12-month period, providing a standardized measure for comparing investment performance. The formula for annualized return takes into account the loan amount, total payment made by the borrower, and the duration of the loan.
GitHub, Website
Let’s connect! I encourage you to like, comment, share, or message me directly with your thoughts on the ideas presented here, or suggestions on interesting topics I should look into going forward.
Top comments (0)