Product Demand Forecasting Research Articles

Utilizing Internet Big Data and Machine Learning for Product Demand Forecasting and Analysis of Its Economic Benefits

Utilizing Internet Big Data and Machine Learning for Product Demand Forecasting and Analysis of Its Economic Benefits

Research on Product Demand Forecasting and Personalized Recommendation Based on Data Analysis

This paper aims to explore the design and implementation of product demand forecasting and personalized recommendation system based on data analysis. Through the collection and analysis of a large number of user behavior data, an accurate demand prediction model is constructed, and based on this, a personalized recommendation algorithm is implemented. The paper first introduces the research background and purpose, and then elaborates the research method, process and results. The method based on data analysis can effectively predict the product demand and provide users with personalized recommendation services, so as to improve user satisfaction and market competitiveness of enterprises.

Role of IT on the Effectiveness of Logistics and Supply Chain Management Systems in the Pharmaceutical Sector in Saudi Arabia Vision 2030

The main objective of this study is to evaluate how IT might improve the efficacy and efficiency of supply chain management and logistics systems in the pharmaceutical sector because the pharmaceutical industry is experiencing a transformation by the lofty objectives outlined by Saudi Arabia Vision 2030. The study was conducted using 150 executives working in the Saudi Arabian pharmaceutical industry's logistics and supply chain division. An open-ended survey questions were used to determine how IT technology affects pharmaceutical logistics and supply chain using non-probability sampling, logistics managers' LinkedIn accounts were selected for the sample, irrespective of the organization's size, location, or gender. SPSS statistical tools were used to analyse the data. It was found that the integration of IT tools and systems has emerged as a crucial enabler in this process. By harnessing the power of data analytics, IoT (Internet of Things), and automation, pharmaceutical companies can gain real-time insights into their supply chains. This, in turn, allows them to develop agile responses to changing market dynamics and customer expectations. Such strategic decisions, driven by IT, enable businesses to adapt quickly, reorganize their operations, and offer value-added services tailored to the specific needs of the market. Moreover, the creative application of IT solutions facilitates efficient inventory management, demand forecasting, and tracking of pharmaceutical products from manufacturing facilities to end consumers results also show that companies may simply increase the pace of the supply chain with the aid of innovative chances in major choices and judgments.

UX Design for an E-commerce Application: A Design Thinking Perspective

The development of e-commerce applications has revolutionized the way people conduct business, but challenges still exist in designing applications that align with user needs and expectations. This study aims to document the design-thinking (DT) approach used in the development of a customized e-commerce application based on the user's perspective, with the goal of extracting the user experience of traditional commerce processes to identify its features. In this study, we focused on the first four phases of DT, which include empathize, define, ideate, and prototype, to gather insights and understand the experiences, needs, pain points, and solutions of the local producers. The data gathered from interviews and observations was subjected to content analysis to identify patterns and themes related to desired features. After analysis, the researchers identified key app features, including integrating data analytics for product performance and demand forecasting, introducing a peer-vendor marketplace, a vendor-managed inventory management system, and a product verification system for authenticity. A mockup prototype design was created and presented to users for feedback. The study highlights the importance of user perspectives in e-commerce app design and the value of design thinking in creating a customized user experience that aligns with user needs.

Market Dynamics: Enhancing Supply Chain Efficiency Through Demand Prediction

This research gives a state-of-the-art solution for web-based demand forecasting. Machine learning methods are employed to build the approach, which takes use of Seasonal Autoregressive Integrated Moving Average (SARIMA) modeling. Customers may utilize our system to provide product codes combined with the period's start and end dates in order to correctly anticipate future demand patterns. Through the combination of previous sales data with current market circumstances, competitive plans, and other external variables, our system is able to discover complicated consumer patterns. This gives data that may be utilized for inventory management, pricing strategies, and production scheduling. All things considered, the holistic plan optimizes resource usage, eliminates waste, and supports consumer satisfaction. A data-driven solution that takes advantage of AI capabilities is being offered as part of this joint endeavor. This solution is positioned to assist numerous sectors, including manufacturing, retail, and healthcare, and it will boost operational efficiency and sustainable development in a global economic framework. Keywords— Product Demand Forecasting, Inventory Management, Production Planning, Time Series Analysis, Predictive Analytics, Inventory Optimization, Demand Prediction System, Real-time Forecasting, Data-driven Decision Making, Supply Chain Optimization, Price Elasticity Analysis, Demand Volatility Management, Retail Analytics.

Demand forecasting of technological products considering re-purchasing and dynamic pricing: a modified diffusion model

Demand forecasting of technological products considering re-purchasing and dynamic pricing: a modified diffusion model

Demand Forecasting Analysis of Body Scrub Product at PT. XYZ Using Autoregressive Integrated Moving Average (ARIMA) Method

PT. XYZ is one of the private companies engaged in the cosmetics industry, especially as a manufacturer of SPA products with natural raw materials. The SPA products produced by PT. XYZ are various kinds of scrubs, body scrubs, masks, essential oils, soaps and other products. Body scrub is the most popular product or best seller in this company. The purpose of this study is to find the best ARIMA model in calculating demand forecasting of body scrub products at PT. XYZ for the period January to December 2024. The method used in this research is the Autoregressive Moving Average (ARIMA) method. There are two ARIMA models that can be used in this study, namely ARIMA (1,1,0) and ARIMA (0,1,1). The selected ARIMA model used to calculate body scrub forecasting at PT. XYZ is the ARIMA (1,1,0) model because it has a smaller error value, namely MSE = 745.46 and MAPE = 7.40%. The results of forecasting the demand for body scrub products at PT. XYZ for the period January to December 2024 using the ARIMA (1,1,0) model show that demand has increased every month with an average demand of 343.4 kg. The error obtained by comparing the forecasting results with the actual sales data for 6 months, namely January - June 2024 is 2.45%, which means that the accuracy of forecasting in 6 months reaches 97.55%.

Time Series Analysis of Product Demand Forecasting and Inventory Optimization on E-commerce Platforms

Time Series Analysis of Product Demand Forecasting and Inventory Optimization on E-commerce Platforms

New product demand forecasting and production capacity adjustment strategies: Within-product and cross-product word-of-mouth

Manufacturers attach increasing importance to consumer word-of-mouth (WOM) as it assists them to improve demand forecasting and determine production capacity adjustment strategies. Communication among potential consumers occurs as a result of within-product and cross-product word-of-mouth. Within-product WOM has received due academic attention touching upon production volume adjustment under infinite capacity, while the impact of cross-product WOM on demand is under-researched with limited number of studies investigating production capacity adjustment. To address this research gap, we employ Agent-based Modeling and Simulation (ABMS) approach and the Bass model, together with considering within-product WOM and cross-product WOM, to modify previous demand forecasting methods and propose production capacity adjustment strategies. Results show: (1) higher performances delivered by manufactures depends more on production capacity adjustment strategies rather than production volume adjustment strategies; (2) production capacity adjustment strategies are closely associated with factors including unit capacity fixed cost and cross-product WOM; (3) on condition of low unit capacity fixed cost, proactive strategy leads to maximal expected net present value (NPV) of profit and minimal lost customer number (LCN); (4) greater within-product WOM and cross-product WOM might not as beneficial as expected, in that expanding within-product WOM and cross-product WOM in most cases leads to growing lost customer number.

Inventory Control for MSME Products Using the Q Model with Lost Sales Condition Based on Products Sales Forecasting

Micro, Small and Medium Enterprises (MSMEs) have an important role in economic development in order to achieve thq quality of economic growth. Intense competition among MSMEs requires MSMEs to have a good inventory control that can help them minimize costs and maximize profits. One of the MSMEs that often experiences problems in inventory control is Sabun Bening Official. To solve the inventory problems in Sabun Bening Official, Holt-Winter Exponential Additive forecasting method is used as a guide to predict future product demand because product demand graph is seasonal and has trend pattern. After getting the value of product demand forecast, inventory control calucaltions are carried out using the Q Model probabilistic inventory method with lost sales condition. The uncertain and fluctuating demand causing the inventory system in Sabun Bening Official is probabilistic and the company will lose sales if it does not able to fulfill customer demands. Based on the research results, product forecasting for the coming period and inventory control policies which include the optimal number of product order, safety stock, reorder point, and product inventory costs can be obtained.

A hybrid deep learning framework with CNN and Bi-directional LSTM for store item demand forecasting

In the era of ever-changing market landscape, enterprises tend to make quick and informed decisions to survive and prosper in the competition. Decision makers within an organization must be supplied with data in a way that could be easily analyzed and comprehended to build strategies in order to achieve business goals. Accurate demand forecasting of products is one of such decisions which is crucial for retail operators to have a clear picture on the future demand of their products and services. With a certainty in estimation, retailers might keep a check on how many items to allocate, order and restock thus boosting their gross sales and profits. Machine Learning approaches are widely used for demand forecasting of different items. In this work, we have used the Store Item Demand Forecasting Challenge dataset from Kaggle to implement our proposed framework. The main novelty of this study was to build a coupled CNN-BiLSTM framework with Lazy Adam optimizer to make an accurate forecast of product demand of store items. Various State-of-art machine learning techniques like SGD (Stochastic Gradient Descent), Linear Regression, K-Nearest Neighbour, Bagging, Random Forest, SVR, XgBoost (extreme gradient boosting) and CNN-LSTM. for demand forecasting has been implemented and the results were compared with the proposed model. On evaluation with metrics including Mean Absolute Percentage Error (MAPE), R-Squared (R2) value and Mean Absolute Error (MAE), it was observed that the proposed framework having more accurecy as compare to the traditional approaches.

Innovation of Economic Management Risk Control in Retailer Supply Chain Based on Differential Equation Model

Abstract This paper constructs the state transition diagram of the retailer’s economic management risk control in the supply chain. At the same time, we construct the differential equation of the model. Based on the differential equation theory, we establish a dynamic equation model for product demand forecasting, which is suitable for the historical data of the retailer’s supply chain. At the same time, we use the two-party game model to determine the strategy choice of maximizing the income of a single enterprise in the secondary supply chain. The study finds that retailers can only maximize revenue through suboptimal order quantities when the financing limit has a substantially limiting effect.

Rethinking Inventory Forecasting Problems in E-commerce: Exploring the effect of integrating forecasting and inventory decisions

Forecasting for inventory control is the process of calculating the inventory needs to fulfill future consumer demand. In general, this process is divided into two sub-processes. The first sub-process receives the current inventory information and forecasts future information, e.g. forecasts future demand from the demand information in the past. The second sub-process uses the forecast information as input to make inventory decisions, e.g. use a product demand forecast to decide how many units of this product to buy. Recent works highlight the importance of integrating forecasting with final inventory decisions, however, there is very little empirical evidence to support that integrating the decision is the best solution. In this work, we propose to explore the effect of integrating the inventory decision into the forecasting problem and compare it with the state-of-the-art approaches. For this, we evaluated the approaches in different operational tasks belonging to our business. Our preliminary findings show that predicting operative decisions instead of demand information could be better and the benefit can be capitalized even in low data scenarios.

A hybrid extreme learning machine model with harris hawks optimisation algorithm: an optimised model for product demand forecasting applications

Accurate and real-time product demand forecasting is the need of the hour in the world of supply chain management. Predicting future product demand from historical sales data is a highly non-linear problem, subject to various external and environmental factors. In this work, we propose an optimised forecasting model - an extreme learning machine (ELM) model coupled with the Harris Hawks optimisation (HHO) algorithm to forecast product demand in an e-commerce company. ELM is preferred over traditional neural networks mainly due to its fast computational speed, which allows efficient demand forecasting in real-time. Our ELM-HHO model performed significantly better than ARIMA models that are commonly used in industries to forecast product demand. The performance of the proposed ELM-HHO model was also compared with traditional ELM, ELM auto-tuned using Bayesian Optimisation (ELM-BO), Gated Recurrent Unit (GRU) based recurrent neural network and Long Short Term Memory (LSTM) recurrent neural network models. Different performance metrics, i.e., Root Mean Squared Error (RMSE), Mean Absolute Percentage Error (MAPE) and Mean Percentage Error (MPE) were used for the comparison of the selected models. Horizon forecasting at 3 days and 7 days ahead was also performed using the proposed approach. The results revealed that the proposed approach is superior to traditional product demand forecasting models in terms of prediction accuracy and it can be applied in real-time to predict future product demand based on the previous week’s sales data. In particular, considering RMSE of forecasting, the proposed ELM-HHO model performed 62.73% better than the statistical ARIMA(7,1,0) model, 40.73% better than the neural network based GRU model, 34.05% better than the neural network based LSTM model, 27.16% better than the traditional non-optimised ELM model with 100 hidden nodes and 11.63% better than the ELM-BO model in forecasting product demand for future 3 months. The novelty of the proposed approach lies in the way the fast computational speed of ELMs has been combined with the accuracy gained by tuning hyperparameters using HHO. An increased number of hyperparameters has been optimised in our methodology compared to available models. The majority of approaches to improve the accuracy of ELM so far have only focused on tuning the weights and the biases of the hidden layer. In our hybrid model, we tune the number of hidden nodes, the number of input time lags and even the type of activation function used in the hidden layer in addition to tuning the weights and the biases. This has resulted in a significant increase in accuracy over previous methods. Our work presents an original way of performing product demand forecasting in real-time in industry with highly accurate results which are much better than pre-existing demand forecasting models.

An Assessment of Smart Factories in Korea: An Exploratory Empirical Investigation

After the Industry 4.0 discussion in Germany in 2011, much attention has been paid to smart factory in Korea. Since 2014, smart factories have been established and expanded in Korea. However, about 80% of them were established at a low level. In this paper, we analyze smart factory statuses in detail through an empirical research on 113 manufacturing companies that have established smart factories in Korea. We build a framework based on the resource-based view (RBV) and IT value creation process and analyze the results of five constructs—manufacturing strategy, organization, system, process, and performance—using basic statistical methodologies to derive the current statuses of manufacturing companies that have established smart factories. Our results show that implementing advanced technologies such as AI technology that can implement semi-finished and finished product quality inspection, manufacturing process optimization and product demand forecast is a challenge, particularly for SMEs. We also find that securing and managing facility data is a difficult problem. In addition, while output and material management ranked high, the utilization of integration systems, which is important when building a smart factory, was found to be extremely low. Lastly, the performance indicator results showed that yield management and defect rate were most important, while job creation through the introduction of smart factories was low. Based on the results of this study, the government may be able to determine effective smart factory policies and provide manufacturing companies with a guide on establishing a smart factory.

FORECASTING GASOLINE DEMAND IN INDONESIA USING TIME SERIES

Fuel is an essential commodity in both the economy and society. Indonesian fuel demand continues to increase annually, whereas fuel production has decreased. Gasoline accounts for more than 50% of fuel consumption for transportation. A reliable gasoline product demand forecast is required to plan the gasoline supply. The objective of this study is to forecast the demand for total gasoline and its three components, which are gasoline 88, gasoline 90, and gasoline 92. This study compared the Holt–Winters additive model and autoregressive integrated moving average for the time-series data for the 2017–2019 period. Because the Holt–Winters additive model generates more accurate results, it was applied to predict the total demand for gasoline during 2020–2022. The results of the combination of the Holt–Winters model and a neural network to forecast gasoline 92 demand had lower errors than the individual Holt–Winters method. The forecast results show that total gasoline demand is forecasted to increase, but the components indicate a different trend. Gasoline 92 and gasoline 88 decreased, but gasoline 90 increased.Keywords: Forecasting, time series, gasoline demand, Holt-Winters, Neural NetworkJEL Classifications: Q4, Q47DOI: https://doi.org/10.32479/ijeep.9982

New Product Demand Forecasting and Inventory Model towards Eyewear Cleaner Product: A Case Study of Nasho Company

Nasho Company is Nano-coating business based on chemicals. This business makes a product called "Nasho Self-cleaning liquid for Glasses" that give ability to protect the glass surface by water repellent, anti-fog, anti-dust, and anti-bacteria. This Company desires to do market expansion by finding an occasion to put the product in local optical stores in Bandung. Yet, the target that they already made needs to be cross-checked. On another hand, the productivity and efficiency of production in this Company are low due to order the material and produce the product only when demand comes. Production planning based on forecasting and inventory model is required for solving this problem. As a result, the Company is able to define their market expansion target as well as their material stocking. This research is using Structured Analogy Forecasting technique to define the forecast for new product and Fixed Order Interval with Safety Stock analysis for material stocking. Mix method is used in this research to gain information and identify the product that would be a benchmark in forecasting technique that in line with Inventory Model analysis. As a result of Structured Analogy forecasting, the benchmark product is Expo lenses cleaner using the judgmental process with thematic analysis and Single Exponential Smoothing with α= 1,92215 is applied with MAPE 6,42%, MAD= 59,68, and MSD= 5362,4, as well as demand in next year, would be 10631 bottles of lenses cleaner liquid. By 95% service level for Fixed Order Interval with Safety Stock, the Company would order; 14 l of Ethanol, 2,5 l Polydimethylsiloxane, 2 l of Isopropyl, 870 unit of the bottle, 13 boxes of wiper, 207 A3+ sheets of box, 25 A3+ sheets of the sticker, and 47 sheets of 1 m HVS of Instruction Paper in every 14 working days.

Analisis Peramalan Permintaan dan Pengendalian Persediaan Bahan Baku Body Scrub Powder di CV. Denara Duta Mandiri

This study aims to analyze the demand forecasting of body scrub powder products in October 2019 and the level of raw material inventory body scrub powder optimal in order to minimize the total cost of inventory in CV. Denara Duta Mandiri. Forecasting analysis using time series model with 3 methods of Moving Averages with 2, 3 and 4 month time period, exponential smoothing method with ? = 0.1, ? = 0.5, ? = 0.9 and Trend Projection. To analyze the value of forecasting accuracy, the method used are Mean Absolute Deviation (MAD) and Mean Squared Error (MSE). The results show that the Trend Projection method is the most effective method that can be used as the basis for determine body scrub powder products demand, with the result of forecasting demand is 562 kg and the value of forecasting accuracy, MAD = 76,97, MSE = 9.760,12. The results of Economic Order Quantity (EOQ) showed that total cost of raw material inventory control body scrub powder at CV. Denara Duta Mandiri by using EOQ smaller than the methods used by the company. CV. Denara Duta Mandiri management should try to apply the EOQ method in terms of supply of raw materials so that the company can better minimize inventory costs. 
 Keywords: demand forecasting, raw material, Economic Order Quantity (EOQ)

Forecasting of Sporadic Products: Practical and Theoretical Considerations

This paper focuses on forecasting of products with sporadic demand. The demand for such products is not continuous but diffused seemingly at random, with a large proportion of zero values in the analyzed time series. The sporadic character of demand patterns actually means that the information available on the demand for previous selling periods is patchy, resulting in lower quality of data available. Under such circumstances demand forecasting is a challenging task. We present the results of a case study, where forecasting practice of a pharmaceutical wholesaler firm –we call it Pharma– is analyzed and developed. We present state-of-the-art knowledge related to demand forecasting of sporadic products and test suggestions related to them. We show that these suggestions can only partly be backed. We extend therefore the suggested product classification scheme and recommend using the concept of demand data aggregation. This will reduce sporadicity and result in higher quality forecasting. Aggregation also helps to specify the recommended forecast period, the length of time recommended to calculate the forecast for. The managerial consequences of these suggestions are also discussed, and future research directions are highlighted.

Gated Recurrent Unit with Genetic Algorithm for Product Demand Forecasting in Supply Chain Management

Product demand forecasting plays a vital role in supply chain management since it is directly related to the profit of the company. According to companies’ concerns regarding product demand forecasting, many researchers have developed various forecasting models in order to improve accuracy. We propose a hybrid forecasting model called GA-GRU, which combines Genetic Algorithm (GA) with Gated Recurrent Unit (GRU). Because many hyperparameters of GRU affect its performance, we utilize GA that finds five kinds of hyperparameters of GRU including window size, number of neurons in the hidden state, batch size, epoch size, and initial learning rate. To validate the effectiveness of GA-GRU, this paper includes three experiments: comparing GA-GRU with other forecasting models, k-fold cross-validation, and sensitive analysis of the GA parameters. During each experiment, we use root mean square error and mean absolute error for calculating the accuracy of the forecasting models. The result shows that GA-GRU obtains better percent deviations than other forecasting models, suggesting setting the mutation factor of 0.015 and the crossover probability of 0.70. In short, we observe that GA-GRU can optimally set five types of hyperparameters and obtain the highest forecasting accuracy.