Machine Learning Framework for Retail Sales Forecasting
DOI:
https://doi.org/10.22399/ijcesen.3993Keywords:
Sales Forecasting, Machine Learning, Retail Analytics, Predictive Modeling, Low-Code Deployment, Feature EngineeringAbstract
Sales forecasting plays a critical role in retail operations, directly impacting inventory management, supply chain planning, and revenue optimization. This paper presents a comprehensive machine learning–based forecasting framework developed for SuperKart, a multi-city retail chain. The proposed approach integrates structured data preprocessing, exploratory data analysis (EDA), feature engineering, and comparative evaluation of regression models including Decision Tree, Random Forest, Gradient Boosting, and XGBoost. Among the tested algorithms, XGBoost outperformed others, achieving an R² score of 0.87 and demonstrating strong generalization on test data. A low-code deployment strategy was implemented using Streamlit and Hugging Face Spaces, enabling business users to generate real-time sales forecasts with minimal technical intervention. This research contributes a scalable, accessible, and data-driven forecasting solution for retail environments, bridging the gap between advanced machine learning techniques and practical business adoption.
References
[1] Forecasting Retail Sales using Machine Learning Models - ResearchGate, accessed September 13,2025:[Online].Available: https://www.researchgate.net/publication/390949992_Forecasting_Retail_Sales_using_Machine_Learning_Models
[2] J. Brownlee, Deep Learning for Time Series Forecasting: Predict the Future with MLPs, CNNs and LSTMs in Python, San Juan, PR, USA: Machine Learning Mastery, 2018. [Online]. Available: https://machinelearningmastery.com/deep-learning-for-time-series-forecasting
[3] L. Breiman, “Random forests,” Machine Learning, vol. 45, no. 1, pp. 5–32, 2001. [Online]. Available: https://link.springer.com/article/10.1023/A:1010933404324
[4] Implementation of Extreme Gradient Boosting (XGBoost) for Retail Sales Prediction, accessed September 13, 2025. [Online]. Available : https://www.researchgate.net/publication/394485351_Implementation_of_Extreme_Gradient_Boosting_XGBoost_for_Retail_Sales_Prediction
[5] T. Chen and C. Guestrin, “XGBoost: A scalable tree boosting system,” in Proc. 22nd ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining (KDD), San Francisco, CA, USA, 2016, pp. 785–794. [Online]. Available: https://doi.org/10.1145/2939672.2939785
[6] Deep learning for time series forecasting: a survey, accessed September 13, 2025. Online]. Available: https://www.researchgate.net/publication/388826200_Deep_learning_for_time_series_forecasting_a_survey
[7] R. J. Hyndman and G. Athanasopoulos, Forecasting: Principles and Practice, 3rd ed. Melbourne, Australia: OTexts, 2021. [Online]. Available: https://otexts.com/fpp3
[8] Data Driven Retail Price Optimization Using XGBoost and Predictive Modeling | Request PDF - ResearchGate, accessed September 13, 2025, https://www.researchgate.net/publication/389356193_Data_Driven_Retail_Price_Optimization_Using_XGBoost_and_Predictive_Modeling
[9] Unlocking Retail Insights: Predictive Modeling and Customer - MDPI, accessed September 13, 2025. [Online]. Available: https://www.mdpi.com/0718-1876/20/2/59
[10] Super kart data set file. [Online] Available: https://github.com/padmanabhamgit/SuperKart/blob/main/SuperKart.csv
[11] Advanced Feature Engineering for Classification - Kaggle, accessed September 13, 2025. [Online]. Available: https://www.kaggle.com/code/azminetoushikwasi/advanced-feature-engineering-for-classification
[12] What is Feature Engineering? - Machine Learning - GeeksforGeeks, accessed September 13, 2025. [Online]. Available: https://www.geeksforgeeks.org/machine-learning/what-is-feature-engineering/
[13] Sales Forecasting Based on Transformer-LSTM Model, accessed September 13, 2025. [Online]. Available: https://www.researchgate.net/publication/379520643_Sales_Forecasting_Based_on_Transformer-LSTM_Model
[14] Best Practices for Time Series Forecasting (Tutorial Paper), accessed September 13, 2025, [Online] Available: https://www.researchgate.net/publication/332079043_Best_Practices_for_Time_Series_Forecasting_Tutorial_Paper
[15] J. H. Friedman, “Greedy function approximation: A gradient boosting machine,” Annals of Statistics, vol. 29, no. 5, pp. 1189–1232, 2001. [Online]. Available: https://projecteuclid.org/journals/annals-of-statistics/volume-29/issue-5/Greedy-function-approximation-A-gradient-boosting-machine/10.1214/aos/1013203451.full
[16] T. Chen and C. Guestrin, “XGBoost: A scalable tree boosting system,” in Proc. 22nd ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining (KDD), San Francisco, CA, USA, 2016, pp. 785–794. [Online]. Available: https://doi.org/10.1145/2939672.2939785
[17] S. Raschka, V. Mirjalili, and J. Hearty, Python Machine Learning, 3rd ed. Birmingham, UK: Packt Publishing, 2019 — includes evaluation metrics (R², RMSE, MAE) and hyperparameter tuning practices. [Online]. Available: https://www.packtpub.com/product/python-machine-learning-third-edition/9781789955750
[18] Samalba/hf-model-ops: MLOps with Hugging Face Spaces and Dagger - GitHub, accessed September 13, 2025. [Online] Available: https://github.com/samalba/hf-model-ops
[19] Best Data Science and Machine Learning Platforms Reviews 2025 ..., accessed September 13, 2025. [Online] Available: https://www.gartner.com/reviews/market/data-science-and-machine-learning-platforms
[20] F. Chollet, Deep Learning with Python, 2nd ed. Shelter Island, NY, USA: Manning, 2021. [Online]. Available: https://www.manning.com/books/deep-learning-with-python-second-edition
[21] Streamlit Spaces - Hugging Face, accessed September 13, 2025. [Online] Available: https://huggingface.co/docs/hub/spaces-sdks-streamlit
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 International Journal of Computational and Experimental Science and Engineering
This work is licensed under a Creative Commons Attribution 4.0 International License.
