Deep Learning for Financial Time Series Forecasting

Student: Vitalii Fishchuk Program: MSc Business Information Technology, University of Twente Period: 2023-2024

Abstract

This thesis investigates the application of deep learning techniques for financial time series forecasting at ING Bank. The research explores various neural network architectures including Long Short-Term Memory (LSTM) networks, Transformer models, and hybrid approaches for predicting financial metrics.

The study evaluates model performance across different forecasting horizons and compares deep learning methods with traditional statistical approaches. Special attention is given to the interpretability of model predictions in the context of banking operations and regulatory requirements.

Research Questions

  1. How do deep learning architectures compare to traditional methods for financial forecasting?
  2. What is the optimal model architecture for different forecasting horizons?
  3. How can model predictions be made interpretable for business stakeholders?

UT Supervisors

  • Prof. dr. J. van Hillegersberg
  • Dr. M.R. Machado

ING Supervisors

  • Data Science Team, ING Bank

Thesis Repository

The thesis will be available upon completion through the University of Twente repository.