Predicting the Performance of Retail Market Firms: Regression and Machine Learning Methods; Mathematics; Vol. 11, iss. 8

Bibliografiset tiedot
Parent link:Mathematics.— .— Basel: MDPI AG
Vol. 11, iss. 8.— 2023.— Article number 1916, 23 p.
Muut tekijät: Vukovic D. Darko, Spitsina (Spitsyna) L. Yu. Lubov Yurievna, Gribanova E. B. Ekaterina Borisovna, Spitsin V. V. Vladislav Vladimirovich, Lyzin I. A. Ivan Alexandrovich
Yhteenveto:Title screen
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
Текстовый файл
Kieli:englanti
Julkaistu: 2023
Aiheet:
Linkit:https://doi.org/10.3390/math11081916
Aineistotyyppi: Elektroninen Kirjan osa
KOHA link:https://koha.lib.tpu.ru/cgi-bin/koha/opac-detail.pl?biblionumber=686196

MARC

LEADER 00000naa0a2200000 4500
001 686196
005 20260421144949.0
090 |a 686196 
100 |a 20260421d2023 k||y0rusy50 ba 
101 0 |a eng 
102 |a CH 
135 |a drcn ---uucaa 
181 0 |a i   |b  e  
182 0 |a b 
183 0 |a cr  |2 RDAcarrier 
200 1 |a Predicting the Performance of Retail Market Firms: Regression and Machine Learning Methods  |f Darko B. Vukovic, Lubov Spitsina, Ekaterina Gribanova [et al.] 
203 |a Текст  |b визуальный  |c электронный 
283 |a online_resource  |2 RDAcarrier 
300 |a Title screen 
320 |a References: 89 tit 
330 |a 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 
336 |a Текстовый файл 
461 1 |t Mathematics  |c Basel  |n MDPI AG 
463 1 |t Vol. 11, iss. 8  |v Article number 1916, 23 p.  |d 2023 
610 1 |a электронный ресурс 
610 1 |a труды учёных ТПУ 
610 1 |a firm performance 
610 1 |a non-linear models of panel data forecasting 
610 1 |a retail market companies 
610 1 |a profitability prediction 
610 1 |a random effects regression 
610 1 |a machine learning methods 
610 1 |a Random Forest 
610 1 |a long short-term memory 
610 1 |a deep neural network 
610 1 |a portfolio algorithm 
610 1 |a ensemble algorithm 
701 1 |a Vukovic  |b D.  |c economist  |c Leading researcher of Tomsk Polytechnic University  |f 1978-  |g Darko  |9 21109 
701 1 |a Spitsina (Spitsyna)  |b L. Yu.  |c Economist  |c Associate Professor of Tomsk Polytechnic University, Candidate of economic sciences  |f 1976-  |g Lubov Yurievna  |9 18510 
701 1 |a Gribanova  |b E. B.  |g Ekaterina Borisovna 
701 1 |a Spitsin  |b V. V.  |c economist  |c Associate Professor of Tomsk Polytechnic University, Candidate of economic sciences  |f 1976-  |g Vladislav Vladimirovich  |9 15195 
701 1 |a Lyzin  |b I. A.  |c Specialist in the field of informatics and computer technology  |c Programmer of Tomsk Polytechnic University  |f 1993-  |g Ivan Alexandrovich  |9 21998 
801 0 |a RU  |b 63413507  |c 20260421 
850 |a 63413507 
856 4 0 |u https://doi.org/10.3390/math11081916  |z https://doi.org/10.3390/math11081916 
942 |c CF