Exploring predictive prowess of ensemble machine learning models in banking stocks: A technical, fundamental, and macroeconomic analysis
Study evaluates ensemble ML models' predictive performance in banking stocks using integrated technical, fundamental, and macroeconomic analysis across holding periods.
What it examines
This paper examines predictive performance of ensemble machine learning models (Random Forest, Gradient Boosting, XGBoost) on Indian banking stock returns by integrating technical, fundamental, and macroeconomic factors. It aims to improve prediction accuracy over various holding periods and overcome limitations of traditional methods.
What it concludes
The study finds that combining technical, fundamental, and macroeconomic factors significantly enhances stock prediction accuracy, especially with XGBoost. These methods can be applied to improve trading strategies, investment decisions, and further research in multi-factor stock prediction across different asset classes.
Evidence objects
Combining technical, fundamental, and macroeconomic indicators significantly boosts prediction accuracy for Indian banking stocks, achieving over 90% performance for mid- and long-term horizons, while technical metrics drive effective short-term forecasts.
key_findings bullet 1 · key_findings · validation V0
The study utilizes ensemble machine learning techniques like Random Forest, Gradient Boosting, and XGBoost with a dataset of 30 variables across 20 major banks, bridging technical and fundamental analysis approaches.
key_findings bullet 2 · key_findings · validation V0
Surprisingly, macroeconomic signals such as inflation and bond yields influence even short-term stock movements, while comprehensive cross-validation and grid-search optimization ensure rigorous analysis from 2013 to 2022 despite overfitting concerns.
key_findings bullet 3 · key_findings · validation V0
This paper uniquely integrates technical, fundamental, and macroeconomic data within ensemble machine learning models for banking stocks. Its originality lies in a holistic approach that builds on established techniques rather than radical innovations. The work remains compelling for its balanced methodology, offering nuanced insights into corporate and fundamental data for AI-driven stock predictions.
key_findings bullet 4 · key_findings · validation V0
Raw abstract and provenance
The work scrutinises the predictive prowess of ensemble machine learning models, namely Random Forest, Gradient Boosting, and XGBoost, in the domain of stock prediction by training models at two different stages. In stage 1, we restrict our evaluation to 18 technical indicators alongside holding period returns of 20 Indian Banks between January 2013 and March 2022, for short-term (20, 40, and 60 days), medium-term (180 days), and long-term durations (240 days); in stage 2, we further develop the study by including an additional combination of 6 firm-specific fundamental factors and 6 macroeconomic variables along with 18 technical indicators designed using price, volume, and momentum. During stage 1, we observe a modest range of performance, that is, between 62% and 78% across metrics, namely, accuracy score, F1 score, precision values, recall score, and specificity numbers. However, with the inclusion of fundamental and macroeconomic factors in stage 2, we observe a significant improvement in performance metrics to the tune of 90% across models for different holding periods. Particularly, for XGBoost, the reported accuracy range lies between 96% and 98%. Results indicate that while technical indicators are extremely important for short-term returns, the feature importance of fundamental and macroeconomic variables is highlighted during medium-term and long-term, respectively.
Source row: 767 · abstract type: unknown