Credit risk analysis of sme based on financial data

by | Nov 10, 2020 | 0 comments

Application Track:

Ready Made

Code:

REACH-2020-READYMADE-YKT_1

Domain:

Proposed by:

YAPI KREDI TEKNOLOJİ (YKT)

Entity Logo:

Summary of the entity:

Yapı Kredi Teknoloji is a Turkish company that delivers outputs in machine learning, data mining, pattern recognition, artificial intelligence and natural language processing fields and develops mobile applications.

Summary of the challenge:

YKT aims to identify the customers that they are probable to be default through analysing their financial data.

Description:

Small and medium-sized enterprises (SMEs) are a key part of Turkey’s economy, which comprises 91.9 % of all enterprises. One of the main factors for growth of the enterprises is credit opportunities. Thus, credit risk evaluation and loan default risk evaluation became very important to financial institution that provides loan to businesses.

The in-depth credit risk analysis in banks has a very important impact on the quantity of Nonperforming loan detection’s (NPL).Predicting NPL’s before they become non-performing is important for banks since the consequences are excruciating unless provisions are made and for this purpose, early data analytics techniques are used. NPL predictions are aimed to determine the likelihood of a default on credit obligations by corporation or sovereign entity over a particular time horizon.

The motivation is to predict probable NPL’s before they become non-performing to provide institutions enough time to make provisions. This challenge chooses to focus on SME loans since each customer segment has different characteristics and shows different behaviours. YKT aims to identify the customers that they are probable to be default through analysing their financial data. Combining these with the state-of-the-art machine learning methods and experience in the field, YKT intends to predict non-performing loans before 6 months of period and decrease the ratio of NPL.

Expected outcomes:

This challenge is designed to employ Machine Learning (ML) algorithms on financial data. Especially, feature engineering techniques on time series tabular data is focused on during the project development. By monitoring the existing portfolios, it is aimed that %15 of SME’s NPL portfolios can be recovered with early tracking functionalities.

How do we apply?

Read the Guidelines for Applicants

Doubts or questions? Read more about REACH on the About Us page,

have a look at our FAQ section or drop us an email at [email protected].