Forecasting Sustainability Reports with Financial Performance Indicators using Random Forest for Feature Selection and Gradient Boosting for Learning

Authors : Hakan Ayhan Dağıstanlı, Figen Özen, İlkay Saraçoğlu

Pages : 279-302

Doi:10.17134/khosbd.1492365

View : 72 | Download : 61

Publication Date : 2024-11-01

Article Type : Research

Abstract :Problems such as excessive population growth, climate change, loss of biodiversity and resource scarcity in the world have led to an increase in global awareness in companies over the years. Lately companies have started to prefer sustainable models instead of existing economy models. As a result, they have started to prepare a sustainability report that includes social and environmental reports instead of just preparing an economic report. In recent years, the data of the circular economy model, which is a new approach for sustainable development to reach its goals, can also be followed through sustainability reports. Research shows that companies that attach importance to sustainability are seen as valuable by investors and sustainability indices are created in the stock markets of countries. This situation has increased the number of studies examining the impact of sustainability reporting or circular economy on financial performance. Firms want to be included in the sustainability indices in order to attract the attention of the potential investor. In this study, time series data of financial performance of companies in XUSRD are used. On the other hand, contrary to the statistical analyses in the literature, to predict whether companies will take part in XUSRD, a combination of two machine learning methods, namely random forest for feature selection and gradient boosting for learning, is used. In addition, to overcome the problem of data scarcity, the column-wise random shuffling method, which is a proven data augmentation technique in predicting stock market indices, has been used. The results show that the combination of random forest and gradient boosting reaches a test accuracy of 94.74% and outperforms state-of-the art models, namely, k-nearest neighbor, random forest, decision tree, support vector, naive Bayes classifiers that have been used in this study for comparison.
Keywords : Makine Öğrenmesi, BIST Sürdürülebilirlik Endeksi, Finansal Performans, Döngüsel Ekonomi, Gradyan Arttırma