Ensuring the objectivity of the technology for forecasting business process indicators in the field of e-commerce

The object of research is the technology of forecasting business process indicators in the field of e-commerce. These technologies were investigated to identify ways to increase their objectivity. In the process of research, an analysis of input data was performed, time horizons were determined and expected results were formulated. Data normalization was carried out using the minmax method, anomaly detection was based on the standard deviation criterion. The choice of the forecasting method included the use of factual, expert and combined methods. Data processing was performed using the K-means and DBSCAN algorithms. Forecast formation was carried out using retrospective methods with the adjustment of indicators and activation functions. Monitoring and adjustment of forecasts was implemented through the MAPE, RMSE, MAE metrics and error analysis. The accuracy of forecasts was assessed by comparing methods by metrics in different scenarios, which ensured the adaptability of the model to a changing business environment. The proposed approaches integrate modern digital tools: big data analysis, automation of forecasting methods, anomaly processing, scenario approach and neural networks. The objectivity of the technology for forecasting business process indicators in the field of e-commerce ensures increased forecast accuracy, adaptability to a changing market environment, and expands the possibilities for making strategic management decisions. This contributes to increasing the competitiveness of enterprises, their ability to quickly respond to changes in the market situation and improve management processes. Due to increased objectivity of forecasting, enterprises can quickly respond to market changes and optimize resource use. The integration of modern data processing tools and multifactor metrics guarantees the accuracy of forecasts and takes into account complex relationships. This creates a basis for strategic planning, ensures sustainable development of enterprises in the digital economy and allows for increased management efficiency in a dynamic market. The results of the study demonstrate that the adjusted technology for forecasting business process indicators in the field of e-commerce contributes to making informed management decisions focused on long-term effectiveness.

Authors

Institutions

Publication Details

Journal
Technology audit and production reserves
Published
2025-04-09
DOI
https://doi.org/10.15587/2706-5448.2025.326211
Primary Topic
Economic and Technological Systems Analysis
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Ensuring the objectivity of the technology for forecasting business process indicators in the field of e-commerce

Svіatoslav Knіaz, Oleksii Fedorchak, Анатолій Кучер, Yaroslava Moskvyak
Technology audit and production reserves
Economic and Technological Systems Analysis
article

Ensuring the objectivity of the technology for forecasting business process indicators in the field of e-commerce

Svіatoslav Knіaz, Oleksii Fedorchak, Анатолій Кучер, Yaroslava Moskvyak
article en

Abstract

The object of research is the technology of forecasting business process indicators in the field of e-commerce. These technologies were investigated to identify ways to increase their objectivity. In the process of research, an analysis of input data was performed, time horizons were determined and expected results were formulated. Data normalization was carried out using the minmax method, anomaly detection was based on the standard deviation criterion. The choice of the forecasting method included the use of factual, expert and combined methods. Data processing was performed using the K-means and DBSCAN algorithms. Forecast formation was carried out using retrospective methods with the adjustment of indicators and activation functions. Monitoring and adjustment of forecasts was implemented through the MAPE, RMSE, MAE metrics and error analysis. The accuracy of forecasts was assessed by comparing methods by metrics in different scenarios, which ensured the adaptability of the model to a changing business environment. The proposed approaches integrate modern digital tools: big data analysis, automation of forecasting methods, anomaly processing, scenario approach and neural networks. The objectivity of the technology for forecasting business process indicators in the field of e-commerce ensures increased forecast accuracy, adaptability to a changing market environment, and expands the possibilities for making strategic management decisions. This contributes to increasing the competitiveness of enterprises, their ability to quickly respond to changes in the market situation and improve management processes. Due to increased objectivity of forecasting, enterprises can quickly respond to market changes and optimize resource use. The integration of modern data processing tools and multifactor metrics guarantees the accuracy of forecasts and takes into account complex relationships. This creates a basis for strategic planning, ensures sustainable development of enterprises in the digital economy and allows for increased management efficiency in a dynamic market. The results of the study demonstrate that the adjusted technology for forecasting business process indicators in the field of e-commerce contributes to making informed management decisions focused on long-term effectiveness.

Technology audit and production reservesVol. 2(4(82))
Lviv Polytechnic National University (UA)
Openalex Percentile: Top 87%
Economic and Technological Systems Analysis
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.