Matchmaking Algorithm

user_13794602 0
Viewed 356

I'm trying to figure out how to best match a borrower to a lender for a real estate transaction. Let’s say there’s a network of a 1000 lenders on a platform. A borrower would log in, and be asked to provide the following:

  1. Personal Information and Track Record (how many projects they have done, credit score, net worth etc.)
  2. Loan Information (loan size, type, leverage etc.)
  3. Project Information (number of units, floors, location, building type etc.)

On the other side, a lender would provide criteria on which they would agree to lend on. For example, a lender agrees to lend to a borrower if:

  1. They have done more than 5 projects

  2. Credit Score > 700

  3. Net Worth > Loan Amount

  4. $500,000 < Loan Amount < $5,000,000

  5. Leverage < 75%

  6. Building Size > 10 Units

  7. Location = CA, AZ, NY, CO

  8. etc...

I want to create a system that matches a lender to a borrower based on the information the borrower provided and the criteria the lender provided. Ideally, the system would assign a 1000 scores to the borrower that represent the “matchmaking” score for each lender on the platform. A borrower that meets more of the lender’s lending requirements would get a higher score since the match should be better. What machine learning algorithm would be best suited to generate such a score? Or would this problem be solved using combinatorial optimization?

Thanks!

recommendation-engine data-science combinatorics machine-learning algorithm
1 Answers

If you don't have the system yet, you are unlikely to have good data for machine learning.

So write a few custom rules and start collecting data. Once you have data, do something like build a logistic regression for estimating the probability of acceptance. Once the model is good enough to beat your home grown rules in an A/B test, switch to the machine learning model.

But you can't invoke the magic of machine learning until you have data to learn from.

user_5854110
Related