[论文解读] An Estimation of Personnel Food Demand Quantity for Businesses by Using Artificial Neural Networks

M. Hanefi Calp|arXiv (Cornell University)|Feb 5, 2019

Forecasting Techniques and Applications参考文献 19被引用 8

一句话总结

本研究提出了一种基于人工神经网络（ANN）的模型，用于估算企业中每日人员的餐饮需求，使用某私营机构餐厅两年的餐饮消费数据。经过优化的8-10-10-1前馈反向传播网络在训练阶段的决定系数R²达到0.9948，测试阶段的R²为0.9830，平均绝对百分比误差（MAPE）极低，仅为0.003783，表明该模型具有极高的准确性，并在减少机构餐饮中的食物浪费和运营成本方面展现出强大潜力。

ABSTRACT

Today, many public or private institutions provide professional food service for personnels working in their own organizations. Regarding the planning of the said service, there are some obstacles due to the fact that the number of the personnel working in the institutions is generally high and the personnel are out of the institution due to personal or institutional reasons. Because of this, it is difficult to determine the daily food demand, and this causes cost, time and labor loss for the institutions. Statistical or heuristic methods are used to remove or at least minimize these losses. In this study, an artificial intelligence model was proposed, which estimates the daily food demand quantity using artificial neural networks for businesses. The data are obtained from a refectory database of a private institution with a capacity of 110 people serving daily meals and serving at different levels, covering the last two years (2016-2018). The model was created using the MATLAB package program. The performance of the model was determinde by the Regression values, the Mean Absolute Percentage Error (MAPE) and the Mean Squared Error (MSE). In the training of the ANN model, feed forward back propagation network architecture is used. The best model obtained as a result of the experiments is a multi-layer (8-10-10-1) structure with a training R ratio of 0,9948, a testing R ratio of 0,9830 and an error rate of 0,003783, respectively. Experimental results demonstrated that the model has low error rate, high performance and positive effect of using artificial neural networks for demand estimating.

研究动机与目标

• 为应对由于人员出勤率波动导致的机构餐饮中每日餐饮需求难以预测的挑战。
• 减少因餐饮需求预测不准确而造成的运营损失——包括成本、时间和人力。
• 开发并验证一种基于人工智能的模型，利用人工神经网络实现精确的每日餐饮需求估算。
• 通过回归指标、MAPE和MSE对模型性能进行评估，数据基于真实的餐饮消费记录。

提出的方法

• 该模型采用前馈反向传播神经网络架构，基于某110人规模私营机构餐厅2016–2018年共两年的真实餐饮消费数据进行训练。
• 输入特征包括历史出勤率和餐饮数据，输出为预测的每日餐饮需求量。
• 通过实验优化网络结构，最终确定为具有三层隐藏层的8-10-10-1架构。
• 模型训练与测试使用MATLAB完成，性能通过R²、MAPE和MSE进行评估。
• 通过反向传播算法调整权重以最小化误差，采用基于回归的学习方法。
• 超参数调优聚焦于网络深度和神经元数量，以最大化R²并最小化误差率。

实验结果

研究问题

• RQ1 人工神经网络能否在人员出勤率波动的机构餐饮环境中，准确预测每日餐饮需求？
• RQ2 与传统统计方法或启发式方法相比，该ANN模型在预测准确性和误差率方面的表现如何？
• RQ3 使用真实餐饮消费数据估算餐饮需求时，最优的神经网络架构是什么？
• RQ4 该模型在多大程度上可减少机构餐饮服务中的食物浪费和运营低效？

主要发现

• 表现最佳的模型在训练阶段的决定系数R²达到0.9948，表明与训练数据拟合近乎完美。
• 模型在测试阶段表现出高达0.9830的R²，证实其在未见数据上具有强大的泛化能力。
• 平均绝对百分比误差（MAPE）为0.003783，表明预测误差极低。
• 模型的均方误差（MSE）为0.003783，进一步证实其在需求估算方面具有高度精确性。
• 8-10-10-1前馈反向传播网络结构被确定为本应用的最优架构。
• 结果证实，人工神经网络可显著提升机构餐饮中餐饮需求预测的准确性。