Machine Learning Based Automatic Pricing and Replenishment Decision for Vegetable Products

In a fresh food superstore, vegetable items have a short shelf life due to their short shelf life. Supermarkets usually replenish the goods on a daily basis based on the historical sales and demand of each item. Therefore, in this paper, automatic pricing and replenishment decisions for vegetable items are related to the research. Data preprocessing is carried out first, which contains operations such as dimensionality reduction, outliers, and missing values. Then a correlation analysis model is established to analyze the relationship of vegetables between different categories and single items through correlation coefficients, and it is found that cauliflower and foliage may promote each other or grow synergistically in many aspects, and may be similar in terms of soil requirements, nutrient uptake, or growth cycle, which leads to a strong positive correlation between them in the data. Finally, future vegetable pricing and replenishment decisions were predicted by constructing an LSTM neural network.