TY - JOUR

T1 - Predicting the Performance of Retail Market Firms: Regression and Machine Learning Methods

AU - Вукович, Дарко

AU - Спицына, Любовь

AU - Грибанова, Екатерина

AU - Спицын, Владислав

AU - Лыжин, Иван

PY - 2023/4/18

Y1 - 2023/4/18

N2 - The problem of predicting profitability is exceptionally relevant for investors and company owners. This paper examines the factors affecting firm performance and tests and compares various methods based on linear and non-linear dependencies between variables for predicting firm performance. In this study, the methods include random effects regression, individual machine learning algorithms with optimizers (DNN, LSTM, and Random Forest), and advanced machine learning methods consisting of sets of algorithms (portfolios and ensembles). The training sample includes 551 retail-oriented companies and data for 2017–2019 (panel data, 1653 observations). The test sample contains data for these companies for 2020. This study combines two approaches (stages): an econometric analysis of the influence of factors on the company’s profitability and machine learning methods to predict the company’s profitability. To compare forecasting methods, we used parametric and non-parametric predictive measures and ANOVA. The paper shows that previous profitability has a strong positive impact on a firm’s performance. We also find a non-linear positive effect of sales growth and web traffic on firm profitability. These variables significantly improve the prediction accuracy. Regression is inferior in forecast accuracy to machine learning methods. Advanced methods (portfolios and ensembles) demonstrate better and more steady results compared with individual machine learning methods.

AB - The problem of predicting profitability is exceptionally relevant for investors and company owners. This paper examines the factors affecting firm performance and tests and compares various methods based on linear and non-linear dependencies between variables for predicting firm performance. In this study, the methods include random effects regression, individual machine learning algorithms with optimizers (DNN, LSTM, and Random Forest), and advanced machine learning methods consisting of sets of algorithms (portfolios and ensembles). The training sample includes 551 retail-oriented companies and data for 2017–2019 (panel data, 1653 observations). The test sample contains data for these companies for 2020. This study combines two approaches (stages): an econometric analysis of the influence of factors on the company’s profitability and machine learning methods to predict the company’s profitability. To compare forecasting methods, we used parametric and non-parametric predictive measures and ANOVA. The paper shows that previous profitability has a strong positive impact on a firm’s performance. We also find a non-linear positive effect of sales growth and web traffic on firm profitability. These variables significantly improve the prediction accuracy. Regression is inferior in forecast accuracy to machine learning methods. Advanced methods (portfolios and ensembles) demonstrate better and more steady results compared with individual machine learning methods.

KW - Random Forest

KW - deep neural network

KW - ensemble algorithm

KW - firm performance

KW - long short-term memory

KW - machine learning methods

KW - non-linear models of panel data forecasting

KW - portfolio algorithm

KW - profitability prediction

KW - random effects regression

KW - retail market companies

UR - https://www.mendeley.com/catalogue/f6df9ee8-70d5-3e39-9954-73ad3170773a/

U2 - 10.3390/math11081916

DO - 10.3390/math11081916

M3 - Article

VL - 11

JO - Mathematics

JF - Mathematics

SN - 2227-7390

IS - 8

M1 - 1916

ER -