PREDICTION OF MACROECONOMIC INDICATOR MOVEMENTS ON CREDIT RISK BASED ON CLIMATE CHANGE

Sierra, Evelyn (2025) PREDICTION OF MACROECONOMIC INDICATOR MOVEMENTS ON CREDIT RISK BASED ON CLIMATE CHANGE. Masters thesis, Institute Technology Sepuluh Nopember.

Text 6025231091-Master_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (3MB)

Abstract

Climate change not only directly affects real sector activities, such as agriculture, manufacturing, construction, trade, and services, but also disrupts the stability of key macroeconomic indicators, including GDP growth, inflation, and unemployment. These indicators have long been used as primary variables in probability of default (PD) prediction models, which fall under the category of credit risk. However, most existing PD prediction approaches remain static, such as logistic regression or decision trees, which assume fixed relationships between macroeconomic variables and credit risk. These models fail to capture time-dependent dynamics or external shocks, such as those caused by climate change, and are often vulnerable to multicollinearity and bias due to suboptimal variable selection. To address these limitations, this thesis proposes a method that models the historical relationship between macroeconomic indicators and default rates using an optimal linear regression approach based on multicollinearity analysis and variable clustering. The macroeconomic indicators are then forecasted using the ARIMA (Autoregressive Integrated Moving Average) model, and the PD prediction is enhanced using a Long Short-Term Memory (LSTM) model that integrates flood data as an exogenous variable to dynamically capture climate-related impacts on financial stability. The research applies a stress testing methodology using LSTM, evaluated over 100 epochs with a final loss value of 0.1138. By leveraging comprehensive macroeconomic and climate datasets, this study develops a prediction model capable of capturing non-linearities and complex interactions among variables. The results are expected to contribute to the development of more robust and accurate credit risk assessment methods in the context of climate change, supporting future financial system stability.

Item Type:	Thesis (Masters)
Subjects:	H Social Sciences > HA Statistics > HA30.3 Time-series analysis H Social Sciences > HA Statistics > HA31.3 Regression. Correlation. Logistic regression analysis. H Social Sciences > HB Economic Theory > Economic forecasting--Mathematical models.
Divisions:	Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Informatics Engineering > 55101-(S2) Master Thesis
Depositing User:	Evelyn Sierra
Date Deposited:	04 Aug 2025 06:33
Last Modified:	04 Aug 2025 06:33
URI:	http://repository.its.ac.id/id/eprint/124889

Actions (login required)

View Item