A Deep Learning‐Based Inventory Management and Demand Prediction Optimization Method for Anomaly Detection

Abstract

The rapid development of emerging technologies such as machine learning and data mining promotes a lot of smart applications, e.g., Internet of things (IoT). The supply chain management and communication are a key research direction in the IoT environment, while the inventory management (IM) has increasingly become a core part of the whole life cycle management process of the supply chain. However, the current situations of a long supply chain life cycle, complex supply chain management, and frequently changing user demands all lead to a sharp rise in logistics and communication cost. Hence, as the core part of the supply chain, effective and predictable IM becomes particularly important. In this way, this work intends to reduce the cost during the life cycle of the supply chain by optimizing the IM process. Specifically, the IM process is firstly formulated as a mathematical model, in which the objective is to jointly minimize the logistic cost and maximize the profit. On this basis, a deep inventory management (DIM) method is proposed to address this model by using the long short-term memory (LSTM) theory of deep learning (DL). In particular, DIM transforms the time series problem into a supervised learning one and it is trained using the back propagation pattern, such that the training process can be finished efficiently. The experimental results show that the average inventory demand prediction accuracy of DIM exceeds about 80%, which can reduce the inventory cost by about 25% compared with the other state-of-the-art methods and detect the anomaly inventory actions quickly.

Predicting Future Demand Analysis in the Logistics Sector Using Machine Learning Methods

“…Based on this model, a deep inventory management (DIM) method utilizing Long Short-Term Memory (LSTM) is proposed. It's noted that this method achieves high accuracy in inventory demand forecasting compared to other approaches [15]. Ribeiro et al (2022) compare the performance of three machine learning models (SVR, Random Forest, and XGBoost), three deep learning models (RNN, LSTM, and GRU), and a classical time series model ARIMA for predicting daily energy consumption.…”

Inventory Optimization Model Design with Machine Learning Approach in Feed Mill Company

“…With this, it manages to generate conclusions, decisions and even insights. [20] The algorithm acquires knowledge through this data and can be improved over time. There are several subdivisions, such as concept learning, decision tree, perception learning, By as learning and reinforced learning [19].…”

“…Machine learning goes distant past making brilliantly machines that are able of learning with designs to act without the require for human insights. [20]. The fast adjustment to the environment of machine learning calculations for the procurement of future information of a framework bolster supervisors in making choices in fabricating forms with the point of progressing the execution of fabricating forms [21].…”

“…Without planning, many things are affected in the company, such as out of stock, that is, it is the lack of the product when the customer is going to buy, with this he will buy from the competition, causing the company to lose an opportunity for gain. Another harmful factor for the organization is the idle stock, the accumulation of products that are not sold and cease to make a profit for the companies [20].…”

“…Through the benefits that a wellmade prediction can bring, machine learning contributes to a more realistic prediction. [20].…”