Advanced Sales Prediction for ERP Systems Using Generative Adversarial Networks |
||
 |
 |
|
| © 2024 by IJCTT Journal | ||
| Volume-72 Issue-8 |
||
| Year of Publication : 2024 | ||
| Authors : Pratiksha Agarwal | ||
| DOI : 10.14445/22312803/IJCTT-V72I8P111 | ||
How to Cite?
Pratiksha Agarwal, "Advanced Sales Prediction for ERP Systems Using Generative Adversarial Networks," International Journal of Computer Trends and Technology, vol. 72, no. 8, pp.80-85, 2024. Crossref, https://doi.org/10.14445/22312803/IJCTT-V72I8P111
Abstract
Enterprise Resource Planning (ERP) systems are integral to modern businesses, providing unified platforms for managing sales, finance, and operations. Accurate sales forecasting within these systems is crucial for strategic planning and operational efficiency. Despite advancements, existing forecasting models often struggle with data sparsity and variability. This paper proposes a hybrid model that combines Generative Adversarial Networks (GANs) with Prophet and Convolutional Neural Networks (CNNs) to enhance forecasting accuracy. GANs generate synthetic data, enriching the training dataset and improving model robustness. The proposed solution integrates GANs with Prophet for improved trend and seasonality predictions and CNNs for capturing temporal dependencies. The GAN model includes a generator to create synthetic data and a discriminator to ensure its realism, which augments the training dataset for both Prophet and CNNs. Experimental results demonstrate significant improvements, with the MAE for Prophet reducing from 112.456 to 97.237 (13.54% improvement) and the MAE for CNN drastically decreasing from 104.342 to 0.00086. This enhancement underscores the effectiveness of GANs in addressing data limitations and enhancing predictive performance. The proposed solution offers a robust approach to improving sales forecasts within ERP systems, providing a valuable tool for businesses to optimize decision-making processes.
Keywords
Convolutional Neural Networks (CNNs), ERP sales forecasting, Generative Adversarial Networks (GANs), Prophet model, Time series forecasting.
Reference
[1] Ranjan Kumar Dash et al., “Fine-Tuned Support Vector Regression Model for Stock Predictions,” Neural Computing and Applications, vol. 35, no. 32, pp. 23295-23309, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Mohsin, Muhammad, and Fouad Jamaani, “A Novel Deep-Learning Technique for Forecasting Oil Price Volatility Using Historical Prices of Five Precious Metals in Context of Green Financing-A Comparison of Deep Learning, Machine Learning, and Statistical Models,” Resources Policy, vol. 86, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Kaijian He et al., “Financial Time Series Forecasting with the Deep Learning Ensemble Model,” Mathematics, vol. 11, no. 4, pp. 1-15, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Arsalan Dezhkam, and Mohammad Taghi Manzuri, “Forecasting Stock Market for An Efficient Portfolio by Combining XGBoost and Hilbert–Huang Transform,” Engineering Applications of Artificial Intelligence, vol. 118, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Konstantinos Oikonomou, and Dimitris Damigos, “Short Term Forecasting of Base Metals Prices Using a LightGBM and A LightGBMARIMA Ensemble,” Mineral Economics, pp. 1-13, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Jinxin Xu et al., “A K-Means Algorithm for Financial Market Risk Forecasting,” arXiv, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Krishna Kumar Gupta, and Sanjay Kumar, “K-Means Clustering Based High Order Weighted Probabilistic Fuzzy Time Series Forecasting Method,” Cybernetics and Systems, vol. 54, no. 2, pp. 197-219, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Htet Htet Htun, Michael Biehl, and Nicolai Petkov, “Survey of Feature Selection and Extraction Techniques for Stock Market Prediction,” Financial Innovation, vol. 9, no. 1, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Sami Ben Jabeur, Salma Mefteh-Wali, and Jean-Laurent Viviani, “Forecasting Gold Price with The XGBoost Algorithm and Shap Interaction Values,” Annals of Operations Research, vol. 334, no. 1, pp. 679-699, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Izza Dinikal Arsy, and Dedi Rosadi, “Measurement of Support Vector Regression Performance with Cluster Analysis for Stock Price Modeling,” Media Statistika, vol. 15, no. 2, pp. 163-174, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Indranil Ghosh, and Pamucar Dragan, “Can Financial Stress be Anticipated and Explained? Uncovering the Hidden Pattern Using EEMDLSTM, EEMD-Prophet, and XAI Methodologies,” Complex & Intelligent Systems, vol. 9, no. 4, pp. 4169-4193, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Taha Buğra Çeli̇k, Özgür İcan, and Elif Bulut, “Extending Machine Learning Prediction Capabilities by Explainable AI in Financial Time Series Prediction,” Applied Soft Computing, vol. 132, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Shikha Verma, and Shiwani Arti, “Prediction of Netflix Stock Prices Using Machine Learning,” Proceedings of D.H.E. Haryana approved National Seminar on Emerging Trends of Technologies in Current Era, pp. 9-14.
[Google Scholar] [Publisher Link]