Customer Demand Data Research Articles

Research on Topology Optimization of Building Digital Supply Chain Based on Genetic Neural Network

In order to maximize the benefit of building supply chain, the topology optimization method of building digital supply chain based on genetic neural network is studied. According to the overall structural characteristics of the building digital supply chain, customer demand data, supplier sales data, manufacturer production management data, and environmental policy exception data are collected to form a building digital supply chain data set. As input data, a building digital supply chain demand prediction model based on improved genetic LSTM neural network is constructed. Capture the needs of the building digital supply chain; according to the demand of suppliers, manufacturers and customers in building digital supply chain, a nonlinear 0–1 mixed integer programming model based on the newsboy model is established. According to the various information provided by the supplier, the ant colony algorithm is used to calculate the optimal supplier. After all suppliers are identified, the topology of the digital supply chain is constructed. So far, the optimization of the supply chain has been completed. The experimental data show that this method can accurately predict the demand of construction projects, the maximum error is less than 1.5%, and can obtain the best supplier selection results. Compared with before optimization, the profit of the structural digital supply chain after topology optimization increases the most.

RFM user value tags and XGBoost algorithm for analyzing electricity customer demand data

With the increasing demand for electricity, predicting user electricity demand has become an essential task. The electricity demand characteristics of users in the electricity market are different, so it is necessary to classify and predict users. Aiming at the above problems, a classified forecasting model of electricity demand based on recent consumption, frequency, monetary (RFM), K-means, XGBoost and dynamic time warping (DTW) algorithm is proposed. The experiment showcases that among the electricity consumption of commercial users, the first type of load has the lowest proportion in autumn, at around 18.6 %; The second type of load has the highest proportion in autumn, about 81.3 %; Accurate classification has been made for the consuming quantity of electricity of commercial users. The average error in the forecasting results of the RFM-KM-XGboost model and the actual value of commercial electricity demand is about 0.07 kW; The average errors between the forecasting results of SVM model and RF model and the true values are about 0.2 kW and 0.14 kW, respectively; It indicates that the forecasting error of the RFM-KM-XGBoost model is smaller. The above results indicate that the RFM-KM-XGBoost model can extract users' electricity demand characteristics by classifying user types and load types, and make more accurate predictions of electricity demand for different types of users.

A Furniture Sales Profit Using the Tsukamoto Method

Abstract. Optimal profit can be achieved through maximum sales results with minimal costs. Besides meeting market demand, cost utilization is also a crucial factor in determining optimal outcomes (Muflikhudin 2021). To address the challenges faced by the discount store in Sampit, several necessary steps should be taken. These include analyzing customer demand data by having the store owner pay attention to frequently requested items. Additionally, enhancing product availability by increasing inventory levels and implementing more effective inventory management systems through various methods to prepare product stocks (Beu and Husna 2019). The aim of this research is to predict revenue for a specific period based on sales turnover (Rahmawati, Rahima Dina, and Wartono 2020).

Combined Forecasts of Intermittent Demand for Stock-keeping Units (SKUs)

Effective inventory management requires accurate forecasts for stock-keeping units (SKUs), especially for the strategic ones for companies’ operations and after-sales services like providing spare parts. Forecasting is a challenging task for such SKUs as they usually have intermittent demand (ID) patterns, consisting of many periods with zero demand and infrequent demand arrivals. Given the highly uncertain nature of ID for SKUs, this study developed a methodological framework for combining statistical and judgmental forecasts and assessed the performance of the proposed framework by using accuracy and bias measures. The forecasting process has several steps, including data preparation, data categorization based on demand patterns, generating statistical and judgmental forecasts, combining statistical and judgmental forecasts, and evaluating the forecast performance. These steps were illustrated on a real-world dataset that contains monthly customer demand data for after-sales spare parts. Results showed that combination is the best method for the majority of SKUs. This paper contributes to the limited literature by addressing the gap between the combined and ID forecasts. The proposed framework gives practitioners and researchers a comprehensive overview to help them make more accurate forecasts while encouraging the use of simple but structured approaches.

An efficient production planning approach based demand driven MRP under resource constraints

Production plans based on Material Requirement Planning (MRP) frequently fall short in reflecting actual customer demand and coping with demand fluctuations, mainly due to the rising complexity of the production environment and the challenge of making precise predictions. At the same time, MRP is deficient in effective adjustment strategies and has inadequate operability in plan optimization. To address material management challenges in a volatile supply-demand environment, this paper creates a make-to-stock (MTS) material production planning model that is based on customer demand and the demand-driven production planning and control framework. The objective of the model is to optimize material planning output under resource constraints (capacity and storage space constraints) to meet the fluctuating demand of customers. To solve constrained optimization problems, the demand-driven material requirements planning (DDMRP) management concept is integrated with the grey wolf optimization (GWO) algorithm and proposed the DDMRP-GWO algorithm. The proposed DDMRP-GWO algorithm is used to optimize the inventory levels, shortage rates, and production line capacity utilization simultaneously. To validate the effectiveness of the proposed approach, two sets of customer demand data with different levels of volatility are used in experiments. The results demonstrate that the DDMRP-GWO algorithm can optimize the production capacity allocation of different types of parts under the resource constraints, enhance the material supply level, reduce the shortage rate, and maintain a stable production process.

An intelligent design for remanufacturing method based on vector space model and case-based reasoning

Design for Remanufacturing (DfRem) plays an important role in remanufacturing, which promotes the product remanufacturability, and enhance the efficiency of remanufacturing processes. However, due to the large and fuzzy demand data, it is difficult to accurately extract DfRem targets from the customer demand data. Moreover, the process of DfRem scheme generation includes conceptual design, general design and detailed design. The remanufacturability of products needs be considered at the design process, which makes the DfRem scheme solution process very complicated. For the purpose of accurately extracting DfRem targets and shortening design cycle, it is necessary to apply intelligent technology for customer demand analysis and DfRem solution. To address this, an intelligent DfRem method based on vector space model (VSM) and case-based reasoning (CBR) is proposed. Firstly, for accurate extraction of DfRem targets, VSM is employed to extract customer demand data features from the mass customer demand data embedded with remanufacturing information, and K-means technique is applied to classify customer demand data features thus to extract DfRem targets. After extraction of DfRem targets, CBR is utilized to retrieve the case that is most similar to the DfRem targets from DfRem and remanufacturing process knowledge bases. In order to improve the accuracy of the retrieval, ontology is used to construct standard knowledge expression. Finally, this method has been evaluated utilizing the DfRem of clutch remanufacturing as case studies. The results show that the method can accurately generate design scheme to satisfy the customer demands. In this paper, the intelligent DfRem method has been developed by Visual Studio and Microsoft SQL Server, which can quickly generate the most suitable solution.

Special Issue on Recent Advances in Urban Transport and Logistics Through Optimization and Analytics

There has been a significant body of research on making urban transportation more efficient and sustainable. Planning of urban transportation services is challenging due to the crowded traffic infrastructure, increasing customer expectations, and rules set by municipalities. In recent years, a vast amount of urban transportation data has become available, e.g., travel times and customer demand data. This special issue intends to establish the landscape for the state-of-the-art in urban transportation involving optimization and analytics.

Finding demand patterns in supply chain planning

Advancements in semiconductor industry have resulted in the need for extracting vital information from vast amount of data. In the operational process of supply chain, understanding customer demand data provides important insights for demand planning. Clustering analysis offers potential to identify latent information from multitudinous customer demand data and supports enhanced decision- making. In this paper, two clustering algorithms to identify customer demand patterns are presented, namely K-means and DBSCAN. The implementation of both algorithms on the prepared data sets is discussed and their performance is compared. The paper outlines the importance of deciphering valuable insights from customer demand data in the betterment of a distributed cognitive process of demand planning.

Finding demand patterns in supply chain planning

Advancements in semiconductor industry have resulted in the need for extracting vital information from vast amount of data. In the operational process of supply chain, understanding customer demand data provides important insights for demand planning. Clustering analysis offers potential to identify latent information from multitudinous customer demand data and supports enhanced decision- making. In this paper, two clustering algorithms to identify customer demand patterns are presented, namely K-means and DBSCAN. The implementation of both algorithms on the prepared data sets is discussed and their performance is compared. The paper outlines the importance of deciphering valuable insights from customer demand data in the betterment of a distributed cognitive process of demand planning.

Impacts of Demand Data Time Resolution on Estimates of Distribution System Energy Losses

Copper losses in low voltage distribution circuits are a significant proportion of total energy losses and contribute to higher customer costs and carbon emissions. These losses can be evaluated using network models with customer demand data. This paper considers the under-estimation of copper losses when the spiky characteristics of real customer demands are smoothed by arithmetic mean averaging. This is investigated through simulation and by analysis of measured data. The mean losses in cables and equipment supplying a single dwelling estimated from half-hourly data were found to have significant errors of 40%, compared to calculations using high resolution data. Similar errors were found in estimates of peak thermal loading over a half-hour period, with significant variation between results for each customer. The errors reduce as the demand is aggregated, with mean losses for a group of 22 dwellings under-estimated by 7% using half-hourly data. This paper investigates the relationship between the demand data time resolution and errors in the estimated losses. Recommendations are then provided for the time resolution to be used in future measurements and simulation studies. A linear extrapolation technique is also presented whereby errors due to the use of averaged demand data can be reduced.

An integrated supply chain model with dynamic flow and replenishment requirements

Integration and coordination of the informational and logistical functions of the supply chain have the potential to increase a company's competitiveness. In this paper, an integrated supply chain framework is developed that considers three main dimensions of information: customer demand, transportation, and inventory data. These dynamic supply chain data are integrated in an algorithm capable of producing high-quality, minimal cost solutions for the integrated supply chain system. The integrated supply chain model's primary goal is to react effectively and quickly to supply chain disruptions and changes, thereby adding unique flexibility to current supply chain decision support systems. The performance of the proposed algorithm is tested in a dynamic environment by embedding it in the decision-making framework of a supply chain simulation model. Model results demonstrate the algorithm's ability both to improve system performance and to reduce total supply chain costs.

The impact of information enrichment on the Bullwhip effect in supply chains: A control engineering perspective

This paper examines the beneficial impact of information sharing in multi-echelon supply chains. We compare a traditional supply chain, in which only the first stage in the chain observes end consumer demand and upstream stages have to base their forecasts on incoming orders, with an information enriched supply chain where customer demand data (e.g. EPOS data) is shared throughout the chain. Two types of replenishment rules are analysed: order-up-to (OUT) policies and smoothing policies (policies used to reduce or dampen variability in the demand). For the class of OUT policies, we will show that information sharing helps to reduce the bullwhip effect (variance amplification of ordering quantities in supply chains) significantly, especially at higher levels in the chain. However, the bullwhip problem is not completely eliminated and it still increases as one moves up the chain. For the smoothing policies, we show that information sharing is necessary to reduce order variance at higher levels of the chain. The methodology is based on control systems engineering and allows us to gain valuable insights into the dynamic behaviour of supply chain replenishment rules. We also introduce a control engineering based measure to quantify the variance amplification (bullwhip) or variance reduction.

Assessing the effects of operational processes and information systems on inventory performance

Over the past decade, manufacturing firms have implemented enterprise-wide information systems in order to improve their performance. In many cases, the achieved results have been much less than anticipated. Previous research suggests that in order to realize maximum performance improvements it is necessary to access timely and informative customer demand data. While enterprise-wide information systems may contribute to the realization of this objective, operational processes, such as inventory management and mass customization may also be effective in improving the firm’s inventory performance. This paper develops a structural equation model that evaluates the impact of enterprise-wide information systems, along with four operational processes, on inventory performance. The results indicate that the use of operational processes, especially just-in-time (JIT), rather than the use of enterprise-wide information systems, leads to improved performance as measured by inventory speculation, lead times, and turnover ratios.

The balanced allocation of customers to multiple distribution centers in the supply chain network: a genetic algorithm approach

In a typical location–allocation problem, customer demand data are often aggregated according to some arbitrary spatial points (e.g. population centers) or boundaries (e.g. census districts). Since such points or boundaries do not represent true sources of customer demands, allocation of aggregated customers to distribution centers can lead to underutilization of distribution centers and deterioration of customer services. In an effort to design a supply chain network that maintains the best balance of transportation cost and customer service, this paper proposes a new model based on naı̈ve balanced star spanning forest formulation. This model goes beyond traditional mathematical programming by incorporating a genetic algorithm that is proven to be effective in dealing with the NP-hard problem.

Demand forecasting in power distribution systems using nonparametric probability density estimation

Customer demand data are required by power flow programs to accurately simulate the behavior of electric distribution systems. At present, economic constraints limit widespread customer monitoring, resulting in a need to forecast these demands for distribution system analysis. This paper presents the application of nonparametric probability density estimation to the problem of customer demand forecasting using information readily available at most utilities. The method utilizes demand survey information, including weather conditions, to build a probabilistic demand model that expresses both the random nature of demand and its temperature dependence. The paper describes a procedure for developing such a model and its application for demand forecasting based on customer energy usage and outside temperature.

Cost Allocation Considerations and Methods for Electric Rate Analysis and Design for Rural Distribution Systems

The continuing increase in the cost of wholesale and retail electric rates has caused both consumer and regulatory attention to focus on the reasonableness of the rates being charged by utilities. Rate increases generally precipitate concern over discriminatory pricing questions. Because the resolution of rate discrimination issues in part involves a cost allocation study, it is important for the rural electric system to be aware of the general considerations involved in the development of a cost of service study. A complete allocation of electric service costs is not an exact procedure, and any cost allocation effort must also involve an analysis of the assumptions that are a part of the cost of service study, particularly if comprehensive customer demand data are not available. The general considerations involved in developing a cost of service study are outlined to define a technique to evaluate the impact of the assumptions that are a part of the allocation of demand related costs.