Loanzone
Enabling a Micro-finance company to reduce loan default rates
UI/UX Design
Data Engg & Analytics
Mobile App
Loanzone is a micro-financing nbfc targeting businesses who primarily operate in the logistics and transportation sector. They provide vehicle loans to these individuals who wish to buy a vehicle or to expand their existing fleet.
Industry
Finance
Company size
<100+ Employee
What we did
- Data Engg & Analytics
- Mobile App Development
Objective
Loanzone is a micro-financing nbfc targeting businesses who primarily operate in the logistics and transportation sector. They provide vehicle loans to these individuals who wish to buy a vehicle or to expand their existing fleet. Using Arokee, Loanzone requires a simple way to accomplish the following:
Data Warehouse
Connect their data sources to a data warehouse in order to build a unified view or a single source of truth
Dashboards
Visualise current business operations through dashboards
ML Models
Build an alerting system to trigger in case the consignment diverted from the regular or recommended route.
Challenges
The Loan management system data is locked away in the software and only incremental reports are provided to the company upon request. These reports are then analysed separately.
The psychometric analysis are in excel sheets that are also analysed separately. The APIs from the credit rating companies need a tech team to work with them to build an application that can hit the APIs, Parse the response and store it for analysis. These disparate data sources make sense only when they are mapped and available in a single place.
Days to process a loan
0
High loan default rate
Solution
Data Warehouse
The Arokee platform was deployed within the client’s AWS cloud infrastructure.
Their data sources were connected to the syntactic platform via the built-in connectors. These included a MySQL db for the Loan data. An API client which connected to Experian, Equifax, CIBIL and CRISIL to retrieve credit scores and an SFTP which contained the customer’s psychometry analysis.
Using the pipes feature in Syntactic, the data fields were mapped, joined and pushed into AWS Redshift Data Warehouse. The Pipe was also configured to run daily, so that all new incremental data automatically gets updated in Redshift.
Dashboards
Once the data was available in Redshift, Arokee AI’s search based interface provided a single point of entry for all the business visualisation needs.
The client was able to easily query the views and create charts for all the important business metrics that they were tracking. The ability to export this data in CSV enabled their teams to do further analysis in the tools that they were already using.
ML Models
Once the data was in Redshift, the client was able to define the features required for training the model. The loan default likelihood was to be predicted using a logistic regression algorithm from Spark MLLib library.
A pipe with the input data sources , the model and the output Redshift table were defined. The model was trained within the platform and the output was fed into a table in Redshift. The pipe was configured to trigger every time a new applicant was entered into the system.
The client was easily able to integrate the model’s prediction into their loan management system, so that the credit team could rely on this information while processing a loan.
Outcome
With Arokee AI, the company was able to bring in a data science based approach to look after their operations and hence improve customer satisfaction. They could optimise routes and stick to SLAs and Reduce operational costs by equipping drivers with feedback systems. Arokee AI provided them a way to leverage a scalable and flexible data infrastructure for all their data science initiatives.
Cost reduction
0
%
Improved team productivity
Recent Work
Launch your product with Arokee
Partner with us for a digital journey that transforms your business ideas into successful, cutting-edge solutions.
