Improving the Interpretability of Asset Pricing Models by Explainable AI: A Machine Learning-based Approach

被引:0
|
作者
Ferrara, Massimiliano [1 ,2 ]
Ciano, Tiziana [3 ,4 ]
机构
[1] Univ Mediterranea Reggio Calabria, Reggio Di Calabria, Italy
[2] Bocconi Univ, ICRIOS Invernizzi Ctr Res Innovat Org Strategy & E, Milan, Italy
[3] Univ Aosta Valley, Aosta, Italy
[4] Univ Mediterranea Reggio Calabria, Decis Lab, Reggio Di Calabria, Italy
来源
ECONOMIC COMPUTATION AND ECONOMIC CYBERNETICS STUDIES AND RESEARCH | 2024年 / 58卷 / 04期
关键词
asset pricing; Machine Learning; Explainable Artificial Intelligence; SHAPE and LIME; feature; ESG; interpretability; BLACK-BOX;
D O I
10.24818/18423264/58.4.24.01
中图分类号
F [经济];
学科分类号
02 ;
摘要
The study examines the integration of machine learning (ML) techniques and explainable artificial intelligence (XAI) for stock price prediction and the interpretation of predictive models. The aim is to improve the accuracy of short-term price forecasts using advanced models like Random Forest and XGBoost, and to utilise XAI tools such as SHAP and LIME to better understand the contribution of each variable in the predictions. This approach can be particularly useful for investors interested in sustainability-related securities, such as those with high ESG ratings, as it provides a deeper understanding of market dynamics and allows for more informed and transparent investment decisions. The integration of XAI not only enhances prediction accuracy, but also helps mitigate the risks associated with understanding and trusting machine learning algorithms, ensuring that these can be used with greater awareness and control, especially in a complex and regulated context like finance.
引用
收藏
页码:5 / 19
页数:15
相关论文
共 50 条
  • [21] A novel explainable machine learning-based healthy ageing scale
    Stepancic, Katarina Gasperlin
    Ramovs, Ana
    Ramovs, Joze
    Kosir, Andrej
    BMC MEDICAL INFORMATICS AND DECISION MAKING, 2024, 24 (01)
  • [22] Explainable AI in Learning Analytics: Improving Predictive Models and Advancing Transparency Trust
    Liu, Qinyi
    Khalil, Mohammad
    2024 IEEE GLOBAL ENGINEERING EDUCATION CONFERENCE, EDUCON 2024, 2024,
  • [23] A Machine Learning-Based Water Potability Prediction Model by Using Synthetic Minority Oversampling Technique and Explainable AI
    Patel, Jinal
    Amipara, Charmi
    Ahanger, Tariq Ahamed
    Ladhva, Komal
    Gupta, Rajeev Kumar
    Alsaab, Hashem O. O.
    Althobaiti, Yusuf S. S.
    Ratna, Rajnish
    COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE, 2022, 2022
  • [24] Harnessing machine learning models and explainable AI to understand MOOC continuance intention
    Sharma, Vinod
    Mahajan, Yogesh
    Kapse, Manohar
    Deb, Saikat
    INFORMATION DISCOVERY AND DELIVERY, 2025,
  • [25] Prediction of Students' Adaptability Using Explainable AI in Educational Machine Learning Models
    Nnadi, Leonard Chukwualuka
    Watanobe, Yutaka
    Rahman, Md. Mostafizer
    John-Otumu, Adetokunbo Macgregor
    APPLIED SCIENCES-BASEL, 2024, 14 (12):
  • [26] A Fast and Minimal System to Identify Depression Using Smartphones: Explainable Machine Learning-Based Approach
    Ahmed, Md Sabbir
    Ahmed, Nova
    JMIR FORMATIVE RESEARCH, 2023, 7
  • [27] Improving CAT bond pricing models via machine learning
    Goetze, Tobias
    Guertler, Marc
    Witowski, Eileen
    JOURNAL OF ASSET MANAGEMENT, 2020, 21 (05) : 428 - 446
  • [28] Improving CAT bond pricing models via machine learning
    Tobias Götze
    Marc Gürtler
    Eileen Witowski
    Journal of Asset Management, 2020, 21 : 428 - 446
  • [29] Artefact Detection in Chronically Recorded Local Field Potentials: An Explainable Machine Learning-based Approach
    Fabietti, Marcos
    Mahmud, Mufti
    Lotfi, Ahmad
    2022 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2022,
  • [30] Improving machine learning models through explainable AI for predicting the level of dietary diversity among Ethiopian preschool children
    Setegn, Gizachew Mulu
    Dejene, Belayneh Endalamaw
    ITALIAN JOURNAL OF PEDIATRICS, 2025, 51 (01)