The application of neural network in event study

Thumbnail Image

Files

bachelor_Pham_Duc_Thuan_2025.pdf (870.76 KB)

URL

Journal Title

Journal ISSN

Volume Title

School of Business | Bachelor's thesis
Unless otherwise stated, all rights belong to the author. You may download, display and print this publication for Your own personal use. Commercial use is prohibited.

Authors

Date

2025

Department

Mikkelin kampus

Major/Subject

Mcode

Degree programme

(Mikkeli) Bachelor’s Program in International Business

Language

en

Pages

57 + 4

Series

Abstract

Objectives: The study analyses the impact of green policy announcements on the Eurozone financial market by comparing traditional CAPM-based and AI-enhanced event study methodologies. It examines market reaction between green and brown companies taken from the EURO STOXX 50 index, aiming to assess methodological accuracy, market impact significance, and market efficiency. Summary: An extensive literature review is conducted to analyse recent major publications related to the topic and a conceptual framework is built based on findings. A nonlinear autoregressive exogenous artificial neural network is utilized in the methodology to enhance traditional event study. The model is then constructed and optimized to give the best performance. Finally, the results from both methods are compared and their implications are discussed. Conclusion: The findings challenge assumptions about AI's superiority in predicting normal returns when strong linear market relationships exist. The leak of European Green Deal had a notable impact on the Eurozone market, showing signs of gradual information processing rather than the immediate adjustments expected under semi-strong market efficiency. The varying performance between portfolios suggests long-term strategic advantages for green firms despite initial corrections. These results have implications for investment strategies, risk management in carbon-intensive sectors, and the development of policies that anticipate market reaction.

Description

Thesis advisor

Stepanov, Roman

Keywords

event study, neural network, green and brown stocks, green policy announcement, artificial intelligence, deep learning, NARX, EURO STOXX 50

Other note

Citation

Permanent link to this item

https://urn.fi/URN:NBN:fi:aalto-202505113582

Collections

[kand] Kauppakorkeakoulu / BIZ (Open Access)