Enhancing Financial Forecasting in ERP Systems using XGBoost: A Robust Sales Prediction Model

DOI

10.2991/978-94-6463-544-7_26How to use a DOI?

Keywords

Financial forecasting; Enterprise Resource Planning (ERP); XGBoost; sales prediction; machine learning

Abstract

Enterprise Resource Planning (ERP) systems depend on financial forecasting as it helps companies to properly monitor inventory, distribute resources, and make wise strategic decisions. Maintaining a competitive edge in the modern dynamic market environment depends on accurate financial forecasts. Many machine learning (ML) models for financial prediction have now been investigated in detail. These models do, however, have major drawbacks, especially in terms of managing complicated, non-linear interactions inside the dataset and include outside data sources. Furthermore, although still offering useful and practical insights, many modern models struggle to properly transfer knowledge across datasets with different properties. This study offers a robust sales prediction model using XGBoost to solve these variances and improve ERP system financial forecasts. We efficiently prepare the dataset for analysis using mean and mode imputation, one-hot encoding, and Min-Max normalisation among other advanced data preparation methods. Using sophisticated feature engineering techniques, one was able to generate original temporal, interaction, and latency features that effectively capture the several components influencing sales. The model’s hyperparameters are painstakingly tuned to improve performance and reach the target degrees of accuracy and dependability. With an accuracy rate of 99.90% and a test accuracy rate of 97.20%, the XGBoost model proved really well. Using Mean Absolute Error (MAE) in combination with RMSE helps one to demonstrate the validity of these findings by so highlighting the ability of the model to fit fresh data. By using XGBoost’s capacity to manage non-linear correlations and adding other data sources, our approach much improves earlier techniques.

Copyright

© 2024 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Pratiksha Agarwal
PY  - 2024
DA  - 2024/10/17
TI  - Enhancing Financial Forecasting in ERP Systems using XGBoost: A Robust Sales Prediction Model
BT  - Proceedings of the 2nd International Conference on Emerging Technologies and Sustainable Business Practices-2024 (ICETSBP 2024)
PB  - Atlantis Press
SP  - 395
EP  - 407
SN  - 2352-5428
UR  - https://doi.org/10.2991/978-94-6463-544-7_26
DO  - 10.2991/978-94-6463-544-7_26
ID  - Agarwal2024
ER  -