Web system for loans classification

R-language
Angular
API
AWS
DynamoDB

AWS-based API and web interface for performance demonstration of various machine learning algorithms.

We have developed an API and user interface for the R-based backend to demonstrate a classification system for defaulted/non-defaulted loans, the system is based on the following points:

data loading and data encoding for categorical data types,

data normalization and pre-processing,

data sampling,

data classification and cross-validation for robust performance estimation.

Following the data set creation/selection and model setting up, users can access detailed graphic information about the classification performance using such metrics as MSE, Kolmogorov-Smirnov statistics, and ROC curves.

Datasets, models, and evaluation results are available for CSV export.

Key functionality:

Data processing

Dataset creation

Data visualization

CSV export