Project Everest

Experiment Results

[Experiment Results]: Malawi Socon February 19: Revised Risk Profiling Testing

https://projecteverest.crowdicity.com/post/964670

Lean Phase: Customer Segment


Assumption: The previous risk profiling tool was inaccurate (the weightings aren’t accurate or the metrics may not be explanatory), with less than 50% of the defaulting and non-defaulting customers being identified correctly (see data here). This may be due to the scores/weightings not being based on any data, as well as potential irrelevancies in the metrics. Via surveys of the remaining customers, we will be able regress the data to fit a model on which to base our weightings/scores on. The surveys will also enable us to further test the validity and relevance of the metrics. The revised risk profiling tool will be more accurate, with a high percentage of customers being correctly identified as non loan-worthy or loan-worthy.

We will be able to create an accurate risk metric (being the dependent variable), based on repayment rate, pattern, and qualitative questions from the survey.

 

Success Metric:

1) % of defaulting customers would fail the risk profiling survey
2) % of non-defaulting customers would pass the risk profiling survey.

Results

We did not collect a large enough sample to build a statistical The results we have gathered do not have enough validity upon which to base any interpretation.  

Validated Learning

The validated learning around this is that we need to develop:

a) A better way of locating and getting in contact with our customers

b) a better way of collecting information off of our customers

            i) Point of sale

            ii) USSD

            iii) 

Next Move

We need to establish what the easiest ways of establishing a creditworthiness process. 

We should be researching methods that other MFIs around the world use to effectively reach a large market but having an effective set of metrics we can fill out to pass/fail people. 

This research should look down the avenues of:

a) Credit worthiness metrics for different MFIs in different developing countries. The output from this research should be assimilated and from it we can deduce what information we need to be collecting off customers at POS.

b) Research "Red Flags" in terms of credit worthiness for existing MFIs. If there is a (set of) characteristic(s) that would exempt someone from being able to get a loan, then this is information we should be collecting as well. 

Link to results

Attached as files. 

edited on 26th February 2019, 19:02 by Kurt Michl

Andrew Vild 4 months ago

Status label added: Experiment Results

Reply 0

Share