Analyzing annual report financial data to understand its impact on share prices of Indian IT consulting firms using machine learning algorithms
Authors
Gupta, Rushabh
Issue Date
2024
Degree
Master of Science (MSc) in Business Analytics
Publisher
Dublin Business School
Rights holder
Rights
Abstract
Investors, financial analysts and individuals or anyone for that matter can rely on Annual Reports to decide on the firm’s current performance and to understand its business to make calculated plans on their investments. Financial information inside annual reports provides an overview of past performance, how they make use of the external environment for their growth needs, their strategies for growth and their expectations for the future. This research tries to investigate how financial data from annual reports along with market data can be used by ML algorithms like Random Forest (RF), Gradient Boosting Machines (GBM), eXtreme Gradient Boosting (XGB) and CatBoost (CB) to identify most impactful financial features in process of predicting firm’s share price using feature selection techniques like P-IMP, FFS, BFS and RFE. The results suggest that XGB performs the best for this financial dataset of IT consulting firms overall, with a low MAE and MSE score across K-fold validation capturing the variance of data with a high R2 score with less susceptibility to outliers and also being more computationally efficient compared to others. The feature selection methods of P-IMP, FFS, BFS and RFE all concur in outputs highlighting the market data features as most influencing features in predicting share prices followed by balance sheet data features providing an insight into focusing on given list of features. Thus, data present in annual reports can be effectively analyzed using ML algorithms by an individual to make their investment decisions based on firm’s actual performance rather than speculation.