Step 1 – Benchmarking Data

Making sure data is correct prevents Garbage In = Garbage out problem This blog is part 1 of the 3 part series . Introduction While Analyzing any model first step is to benchmark the data that is being used to build the model. The old adage of “Garbage in = Garbage out” can not be more strongly emphasized in case of building ML models. To achieve this task we chose a specific vintage. Chosing Specific vintage allowed us to avoid…

Building your Dream Achiever Portfolio

  Saving money is hard. If by working hard you are able so save some money  investing it intelligently to get good returns that align with your dreams is nearly impossible. At Croudify we are here to help. If you go by default choice of many consumers and put your hard earned money in a savings account you will get a measly return of 0.01 – 0.06% . This means if you Save $10,000 and put it in a savings account…

What I learnt Moderating the Fintech panel at IIT Leadership Conference

  On June 17 I moderated “Fintech , The Path Forward” panel , at IIT leadership Conference in Santa Clara. My three other esteemed panelist were Anju Patwardhan , Senior Partner at CreditEase, Arvind Purushotam , Global Head Citi Ventures & Soups Ranjan , Director Data Science at Coinbase. We had an interesting and engaging discussions covering wide range of topics related to Fintech industry in US, Europe and Asia. With experience from the biggest P2P company in the world,…

Online Lenders are doing a good job of identifying the frauds (even without hard income verification)

Default Rate for Verified vs Non Verified Income - Lending Club

Recently there was an article in Bloomberg (Article Link) that talked about how online lenders are not always verifying the basic borrower information like Income. Subsequently it got picked up by websites like Yahoo & Business Insider (Article Link) generating some sensational headlines. Though both articles did mention that sites like Lending Club use various indicatiors and some Machine Learning models to determine whether they need a manual verification of the income, but that detail was hidden. We at Croudify…

Why build a Proprietary Default Model ?

Default Modeling has been the backbone for all credit decisions in the Banking industry for nearly five decades. The models can vary from as rudimentary as simple bucketing to sophisticated models that use derived risk factors, Markov chains and Machine Learning. At Croudify Ratings when we started looking at the risk ratings available at various platforms we soon realized that we need a risk model of our own. All platforms have proprietary models that use different criteria to rate loans. This…

Simplified Secondary Market Investing on Lending Club

Investors in P2P loans have long wished to get some guidance on pricing and risk when trading on secondary markets like folioFn (or private platforms for whole loans). Till date the only thing they could do was ad-hoc analysis basis on some factors but it made most uncomfortable. The questions like how is this the right price ? Will prepayment of this performing loan result in a loss if I pay a premium always haunted us. Enter Croudify !!! a trading platform provides…