Abstract
A key metric for improving business cafeteria operations, inventory control, and customer satisfaction is accurate sales forecasting. k-Nearest Neighbors (k-NN) and other standard machine learning algorithms usually fail to identify temporal patterns in sales data, which leads to predictions that are not accurate. We provide a better forecasting technique that overcomes this limitation by utilizing Long Short-Term Memory (LSTM) networks, a specific kind of recurrent neural network that can recognize long-term dependencies in sequential data. The performances of LSTM and k-NN were compared and evaluated using a Kaggle corporate cafeteria sales dataset. Based on experimental results, the LSTM model outperformed k-NN with a mean prediction accuracy of 87.57% compared to 83.99%. The significance of the improvement (p = 0.038) was validated by statistical testing with an independent samples t-test.
References
Schmidt, Austin, Md Wasi Ul Kabir, and Md Tamjidul Hoque. "Machine learning based restaurant sales forecasting." Machine Learning and Knowledge Extraction 4, no. 1 (2022): 105-130.
Lasek, Agnieszka, Nick Cercone, and Jim Saunders. "Restaurant sales and customer demand forecasting: Literature survey and categorization of methods." International Summit, Smart City 360° (2015): 479-491.
Bandara, Kasun, Peibei Shi, Christoph Bergmeir, Hansika Hewamalage, Quoc Tran, and Brian Seaman. "Sales demand forecast in e-commerce using a long short-term memory neural network methodology." In International conference on neural information processing, Cham: Springer International Publishing, (2019): 462-474.
Carbonneau, Real, Kevin Laframboise, and Rustam Vahidov. "Application of machine learning techniques for supply chain demand forecasting." European journal of operational research 184, no. 3 (2008): 1140-1154.
Tanizaki, Takashi, Tomohiro Hoshino, Takeshi Shimmura, and Takeshi Takenaka. "Demand forecasting in restaurants using machine learning and statistical analysis." Procedia CIRP 79 (2019): 679-683
Sanjana Rao, G. P., K. Aditya Shastry, S. R. Sathyashree, and Shivani Sahu. "Machine learning based restaurant revenue prediction." In Evolutionary Computing and Mobile Sustainable Networks: Proceedings of ICECMSN 2020, Singapore: Springer Singapore, (2020): 363-371.
Sakib, SM Nazmuz. "Restaurant sales prediction using machine learning." In Handbook of research on AI and machine learning applications in customer support and analytics. IGI Global, (2023): 202-226.
Stergiou, Konstantinos, and Theodoros E. Karakasidis. "Application of deep learning and chaos theory for load forecasting in Greece." Neural Computing and Applications 33, no. 23 (2021): 16713-16731.
Hochreiter, Sepp, A. Steven Younger, and Peter R. Conwell. "Learning to learn using gradient descent." In International conference on artificial neural networks, Berlin, Heidelberg: Springer Berlin Heidelberg, (2001): 87-94.
Rácz, Anita, Dávid Bajusz, and Károly Héberger. "Effect of dataset size and train/test split ratios in QSAR/QSPR multiclass classification." Molecules 26, no. 4 (2021): 1111.
Cortez, Bitzel, Berny Carrera, Young-Jin Kim, and Jae-Yoon Jung. "An architecture for emergency event prediction using LSTM recurrent neural networks." Expert Systems with Applications 97 (2018): 315-324.
Dai, Yun, and Jinghao Huang. "A sales prediction method based on lstm with hyper-parameter search." In Journal of Physics: Conference Series, vol. 1756, no. 1, p. 012015. IOP Publishing, 2021.
Chniti, Ghassen, Houda Bakir, and Hédi Zaher. "E-commerce time series forecasting using LSTM neural network and support vector regression." In Proceedings of the international conference on big data and Internet of Thing, (2017): 80-84.
Hu, Li-Yu, Min-Wei Huang, Shih-Wen Ke, and Chih-Fong Tsai. "The distance function effect on k-nearest neighbor classification for medical datasets." SpringerPlus 5, no. 1 (2016): 1304.
Kumar, Jitendra, Rimsha Goomer, and Ashutosh Kumar Singh. "Long short term memory recurrent neural network (LSTM-RNN) based workload forecasting model for cloud datacenters." Procedia computer science 125 (2018): 676-682.
Rácz, Anita, Dávid Bajusz, and Károly Héberger. "Effect of dataset size and train/test split ratios in QSAR/QSPR multiclass classification." Molecules 26, no. 4 (2021): 1111.
Samonte, P. M. J., Elixeline Britanico, Karmin Eda Mae Antonio, J. E. J. De la Vega, Tia Julienne P. Espejo, and Danielle C. Samonte. "Applying deep learning for the prediction of retail store sales." In Proceedings of the International Conference on Industrial Engineering and Operations Management, vol. 10. 2022.
https://www.kaggle.com/c/restaurant-revenue-prediction/data.