Accurate forecasting is critical for effective warehouse network planning and inventory management in e-commerce. This study tackles these challenges by applying a differentiated forecasting strategy over a three-month period. The Autoregressive Integrated Moving Average (ARIMA) model is used for monthly inventory predictions, while the Long Short-Term Memory (LSTM) neural network is employed for daily sales forecasts. Experimental validation across 350 product categories demonstrates the efficacy of this approach. ARIMA effectively captured dynamic inventory trends (e.g., Category 1 showing gradual increases; Category 91 depleting from 3824 to 0). Concurrently, LSTM successfully modeled complex daily sales fluctuations (e.g., Category 61 peaking at 3693 units on 21 July; Category 31 consistently recording zero sales). This dual-model strategy, leveraging the complementary strengths of ARIMA for relatively stable monthly inventory series and LSTM for volatile daily sales patterns, provides a robust, data-driven basis for optimizing warehouse resource planning and product category allocation. Furthermore, visualization of categorized forecast results reveals distinct sales distribution patterns, thereby enabling enterprises to refine inventory and sales strategies with greater precision, leading to reduced redundant space investment and improved resource allocation efficiency. Future research will focus on incorporating multivariate interactions to further enhance model practicality and predictive power.

The exponential development of e-commerce in recent decades has enhanced convenience for individuals. Compared to the conventional business environment, e-commerce is characterized by increased dynamism and complexity, resulting in several obstacles. Data mining assists individuals in effectively addressing these difficulties. Traditional data mining cannot efficiently use big data in the power provider industry. It heavily relies on time-consuming and labor-intensive feature engineering, and the resulting model could be more easily scalable. Convolutional Neural Networks (CNN) can efficiently use vast amounts of data and autonomously extract valuable elements from the original input, resulting in increased effectiveness. This article utilizes a CNN to extract valuable insights from e-commerce information to forecast commodities sales accurately and proposes a CNN-based Sales Forecasting Model (CNN-SFM). The findings indicate that using data mining and CNN yields a high level of precision in forecasting forthcoming people buying capacity data. The correlation variable between actual usage information and projected usage information was 0.98, and the highest mean error was just 1.78%. Data mining can effectively extract hidden relevant information and forecast future consumption habits for e-commerce systems. CNN demonstrates proficiency in accurately predicting forthcoming consumption power and trends.

This study addresses the strategic challenges faced by a company specialising in the manufacture of oil and gas equipment. Following organisational restructuring, which involved the dissolution of one business unit and the creation of another, the company is navigating complexities in product focus and manpower allocation within the Asia-Pacific region. The research problem centres on identifying the top-performing product, determining potential countries for establishing a support base facility based on sales performance, and developing a method for forecasting future sales. The research involved retrieving and pre-processing historical sales data, then performing a thorough descriptive and predictive analysis. The data was partitioned into training and testing sets to facilitate predictive analytics. Several predictive models were developed and tested, including neural networks, linear regression, gradient-boosted trees, random forests, and ARIMA methods. Tableau Public was utilised for descriptive analytics, whereas RapidMiner Studio was employed for predictive analytics. The study’s results, derived through both descriptive and predictive analytic methods, reveal critical insights. The Blowout Preventer (BOP) emerged as the top-performing product in the Asia-Pacific region. In terms of establishing support base facilities, Malaysia was identified as the ideal location for the BOP, while Indonesia was found suitable for the Manifold product group. Furthermore, the Random Forest model was determined to be the most effective for forecasting future sales. These findings provide strategic guidance for the company in product focus, regional expansion, and resource allocation, contributing significantly to the company’s decision-making process in a competitive industry.

The intensification of market competition makes refined operation management become the focus of attention of major manufacturers. As an important branch of artificial intelligence (AI), machine learning (ML) plays a key role in it, and has its application prospect in various systems. Based on this situation, this paper takes vending machines as the research object. On the one hand, the product classification model of vending machine is constructed based on decision tree algorithm. On the other hand, based on neural network (NN), the sales forecast model of vending machines is built. Finally, based on the above research, the theoretical framework of decision support system (DSS) for vending machines is constructed. The research shows that: (1) The accuracy of C4.5 algorithm can reach 87 % at the highest and 68 % at the lowest. The accuracy of the improved C4.5 algorithm can reach 87 % at the highest and 67 % at the lowest, with little difference between them. (2) The maximum running time of the improved C4.5 algorithm is about 5500 ms, and the minimum is close to 1 ms. In addition, the running time of all seven datasets is better than that of the unmodified algorithm. (3) When the back propagation neural network (BPNN) is used to forecast the sales of vending machines, the curve of the predicted data basically coincides with the curve of the actual data, which shows that its accuracy is high. This paper aims to build a convenient and secure DSS by taking vending machines as an example. In addition, this paper also uses reinforcement learning to optimize the research methods of this paper. It can further optimize the performance and efficiency of vending machines and provide better service experience for customers. Meanwhile, the use of reinforcement learning can make the whole system more intelligent and adaptive to better cope with the changing market environment.

In today’s competitive market, sales forecasting of newly released and short-term products is an important challenge because there is not enough sales data. To address these challenges, we propose a sales forecasting model for new-released and short-term products and study the case of mobile phones. The main approach is to develop an integrated sales forecasting model by training the sales patterns and product characteristics of the same product category. In particular, we analyze the performance of the latest 12 machine learning models and propose the best performance model. Machine learning models have been used to compare performance through the development of Ridge, Lasso, Support Vector Machine (SVM), Random Forest, Gradient Boosting Machine (GBM), AdaBoost, LightGBM, XGBoost, CatBoost, Deep Neural Network (DNN), Recurrent Neural Network (RNN), and Long Short-Term Memory (LSTM). We apply a dataset consisting of monthly sales data of 38 mobile phones obtained in the Korean market. As a result, the Random Forest model was selected as an excellent model that outperforms other models in terms of prediction accuracy. Our model achieves remarkable results with a mean absolute percentage error (MAPE) of 42.6258, a root mean square error (RMSE) of 8443.3328, and a correlation coefficient of 0.8629.

Sales forecasting is the methodology of predicting future values from a known time series data. The preference methodology of sales forecast is selected based on the minimum of the forecast errors given. Knowing that we are persevering in the VUCA realm now, it becomes a challenge for the business to improve the forecast accuracy. The leaders not only focus on agility and resilience in the VUCA environments, but also ensure that all insights, intelligence, and data feed innovation processes continuously. New skills and tools should be used to design and predict in an organisation. Hence, sales forecasting is essential nowadays to ensure our business resilience to the VUCA environment and continuous sustain in this competitive global marketplace. This study aims to identify the preference quantitative methodology: exponential smoothing (ES) or autoregressive integrated moving average (ARIMA) provide more accurate of sales forecasting compared with current practice – judgmental approach for the organisation in this VUCA environment.

This study predicts product sales based on product sales during the trial period and text mining of online reviews of products. This study uses the BERT model to judge the sentiment tendency of reviews and identify product attributes, build a sales forecast model based on the extracted review features and the sales and product features during the trial sales period, and evaluate the effect of the forecast model. Among the prediction models constructed in the study, the multiple linear regression model has the worst effect, the prediction effect of random forest and BP neural network is close, and the prediction effect of XGBoost model is the best.

An approach for sales forecasting

The establishment of enterprise target inventory is directly related to the forecast of drug sales volume. Accurate sales forecasting can help businesses not only set accurate target inventory but also avoid inventory backlogs and shortages. In this paper, NN technology is used to forecast sales and is optimized using the PSO algorithm, resulting in the creation of a drug sale forecast model. The model optimizes the weights and thresholds of NN using the improved PSO optimization algorithm and predicts the periodic components based on time correlation characteristics, effectively describing the trend growth and seasonal fluctuations of sales forecast data. Furthermore, the model in this paper has been creatively improved according to the needs of practical application, which has improved the shortcomings of traditional NN, such as long training time, slow convergence speed, and ease to fall into local minima, to improve performance and quality, and has received positive results in application. The experimental results show that this model has a prediction accuracy of 96.14 percent, which is 12.78 percent higher than the traditional BP model. The optimized model can be used to forecast drug sales in a practical and feasible way.

Automotive aftermarket industry is possessed of a wide product portfolio range which is in the 4th rank by its worldwide trade volume. The demand characteristic of automotive aftermarket parts is volatile and uncertain. Nevertheless, the cause-and-effect relationship of automotive aftermarket industry has not been defined obviously heretofore. These conditions bring automotive aftermarket sales forecasting into a challenging process. This paper is composed to determine the relevant external factors for automotive aftermarket sales based on expert reviews and to propose a sales forecasting model for automotive aftermarket industry. Since computational intelligence techniques yield a framework to focus on predictive analytics and prescriptive analytics, an artificial neural network model constructed for Turkey automotive aftermarket industry. Artificial intelligence is a subset of computational intelligence that focused on problems which have complex and nonlinear relationships. The data which have complex and nonlinear relationships could be modelled successfully even though incomplete data in case of implementation of appropriate model. The proposed ANN model for sales forecast is compared with multiple linear regression and revealed a higher prediction performance.

Sellers readily obtain consumer product evaluations from online reviews in order to identify competitive products in detail and predict sales. Firstly, we collect product review data from shopping websites, social media, product communities, and other online platforms to identify product competitors with the help of word-frequency cooccurrence technology. We take mobile phones as an example to mine and analyze product competition information. Then, we calculate the product review quantity, review emotion value, product-network heat, and price statistics and establish the regression model of online product review forecasts. In addition, the neural-network model is established to suggest that the relationships among factors are linear. On the basis of analyzing and discussing the impact of product sales of the competitors, product price, the emotional value of the reviews, and product-network popularity, we construct the sales forecast model. Finally, to verify the validity of the factor analysis affecting the sales and the rationality of the established model, actual sales data are used to further analyze and verify the model, showing that the model is reasonable and effective.

머신 러닝을 활용한 의류제품의 판매량 예측 모델 : 아우터웨어 품목을 중심으로

Purpose – This paper aims to evaluate the performance of the consolidation process of a product recently included commercially in a portfolio through a sales forecasting model that, focused on several segments of the customer portfolio, supports the commercial decision-making.Design/methodology/approach – This approach uses the ABC Curve methodology to define the analysis in segments of relevance and then integrates two methods: (i) the Markovian models in discrete time and annual step to predict the transition behavior between the new replacement product and the consolidated ones; (ii) first-order and second-order exponential smoothing time series forecasting method to predict products in aggregate demand. This model was applied to a seed distributor company based on its customer portfolio and historical data for sales between 2011 and 2019.Findings – The sales forecasting benchmark scenario, designed for stable conditions in the behavioral adherence of new products and the commercial strategy, resulted in a quantitative support for targeting and monitoring commercial efforts to maximize the global performance for this process.Originality/value – Besides presenting a new Markov Chains commercial management approach, the model developed introduces a quantitative tool into the literature for targeting the customer portfolio management processes in the context of replacement in a product portfolio.Keywords - Curve ABC. Markov Chains. Sales Forecasting. Exponential Smoothing. Customer Portfolio Management.

• Decision support for restaurant managers using online reviews and sales data. • Impact on sales forecast is assessed through a dashboard. • Sales forecast model based on TripAdvisor data and the Bass Emotion model. • Restaurant experts highlighted the time saved in the decision-making process. Restaurant management requires customer responsiveness to deal with increasingly higher expectations and market competitiveness. This study proposes an approach to simplify the decision-making process of restaurant managers by combining both live social media customer feedback and historical sales data in a sales forecast model (based on TripAdvisor data and the Bass model). Our approach was validated with internal and external (i.e., online reviews) data gathered from six restaurants. The collected data was processed using data analytics for developing a dashboard that provides value for restauranteurs by taking advantage of online reviews and sales forecast. Such dashboard was evaluated by restaurant management experts, which provided positive feedback, highlighting in particular the time saved in the decision-making process.

Purpose: In recent years, smart retailing has been gradually acknowledged and has slowly impacted countless industries. This study takes smart retailing as the starting point and explores the increased attention on the perishable food (fresh food) market in convenience stores. Remarkable improvements in the general food consumer population in Taiwan and the advent of an aging society with changes in social structure and consumer style are also taken into consideration. As perishable goods (fresh food products) easily spoil, the scrap rate of fresh food in convenience stores has always been a topic of great importance. Design/methodology/approach: Perishable food from well-known convenience store chains in Taiwan is taken as the subject of this study, and sales data of stores in different regions are used to establish sales forecast models for the convenience store chains. The optimal sales forecast model for each store's products was established through a data analysis, and the characteristics and differences of all products are explored to establish decision-making advices for enterprises in ordering perishable food. Multiple stores and perishable foods with two-year sales data of 11 perishable foods in every six stores in different county are adopted to establish the predictive models in this study, including time series, support vector machine (SVM), Lagrangian support vector machine (LSVM), random forest, neural network, generalized linear, and generalized linear mixed models. Findings: Results show that the time series model and SVM have lower prediction error values and better prediction results among all the established sales forecast models. Given the influence of region and population characteristics, varying models are applicable to stores in different regions. Thus, the difficulty of prediction will also vary. Practical implications: Different commodities will have varying levels of prediction difficulty due to dissimilarities in commodity attributes. Convenience stores are generally willing to predict the sales of fresh food through an artificial intelligence model. Different forecasting models should be selected by stores. If one or more forecasting models are used for prediction, the model with a stable forecasting error should be selected for implementation. Originality/value: This research analyzes the products sold in multiple stores and applies different time series and machine learning algorithms to build predictive models. The results show that the most suitable algorithms for stores of products are different. If a convenience store wants to build a predictive model, differentiated models must be established for different stores and commodities.

El presente trabajo tiene como principal objetivo desarrollar una herramienta de control y gestión para el inventario de producto terminado para una empresa industrial con la ayuda de herramientas tecnológicas como Excel y el software R Studio. Por tal razón, se analizarán las variables que intervienen o afectan directa e indirectamente al inventario como: datos históricos de venta, datos atípicos de ventas, pronóstico de demanda futura, modelo de proyección, tiempos de reabastecimiento, nivel de servicio, stock de seguridad, inventario promedio e inventario óptimo. Además, el modelo de optimización del inventario está basado en el análisis estadístico de datos como: coeficientes de variación, desviación estándar, valores mínimos y máximos y cuartiles. Debido a la confiabilidad de los datos e información estratégica de la empresa, el presente estudio tiene sus limitaciones y por lo tanto se generan supuestos que serán detallados para que la herramienta a futuro pueda ser utilizada, evaluada y mejorada según amerite.

A Long Short Term Memory (LSTM) based sales model has been developed to forecast the global sales of hotel business of Travel Boutique Online Holidays (TBO Holidays). The LSTM model is a multivariate model; input to the model includes several independent variables in addition to a dependent variable, viz., sales from the previous step. One of the input variables, “number of active bookers per day”, is estimated for the same day as sales. This need for estimation requires the development of another LSTM model to predict the number of active bookers per day. The number of active bookers is variable, so the predicted is used as an input to the sales forecasting model. The use of a predicted variable as an input variable to another model increases the chance of uncertainty entering the system. This paper discusses the quantum of variability observed in sales predictions for various uncertainties or noise due to the estimation of the number of active bookers. For the purposes of this study, different noise distributions such as normalized, uniform, and logistic distributions are used, among others. Analyses of predictions demonstrate that the addition of uncertainty to the number of active bookers via dropouts as well as to the lagged sales variables leads to model predictions that are close to the observations. The least squared error between observations and predictions is higher for uncertainties modeled using other distributions (without dropouts) with the worst predictions being for Gumbel noise distribution. Gaussian noise added directly to the weights matrix yields the best results (minimum prediction errors). One possibility of this uncertainty could be that the global minimum of the least squared objective function with respect to the model weight matrix is not reached, and therefore, model parameters are not optimal. The two LSTM models used in series are also used to study the impact of corona virus on global sales. By introducing a new variable called the corona virus impact variable, the LSTM models can predict corona-affected sales within five percent (5%) of the actuals. The research discussed in the paper finds LSTM models to be effective tools that can be used in the travel industry as they are able to successfully model the trends in sales. These tools can be reliably used to simulate various hypothetical scenarios also.

In reality, there are so-called holiday effects in the sales of many consumer goods, and their sales data have the characteristics of double trend change of time series. In view of this, by introducing the seasonal decomposition and ARIMA model, this paper proposes a sales forecasting model for the consumer goods with holiday effects. First, a dummy variable model is constructed to test the holiday effects in consumer goods market. Second, using the seasonal decomposition, the seasonal factor is separated from the original series, and the seasonally adjusted series is then obtained. Through the ARIMA model, a trend forecast to the seasonally adjusted series is further carried out. Finally, according to the multiplicative model, refilling the trend forecast value with the seasonal factor, thus, the final sales forecast results of the consumer goods with holiday effects can be obtained. Taking the cigarettes sales in G City, Guizhou, China as an example, the feasibility and effectiveness of this new model is verified by the example analysis results.

The objective of the industry in general, and of the chemical industry in particular, is to satisfy consumer demand for products and the best way to satisfy it is to forecast future sales and plan its operations.Considering that the choice of the best sales forecast model will largely depend on the accuracy of the selected indicator (Tofallis, 2015), in this work, seven techniques are compared, in order to select the most appropriate, for quantifying the error presented by the sales forecast models. These error evaluation techniques are: Mean Percentage Error (MPE), Mean Square Error (MSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), Mean Absolute Scaled Error (MASE), Symmetric Mean Absolute Percentage Error (SMAPE) and Mean Absolute Arctangent Percentage Error (MAAPE). Forecasts for chemical product sales, to which error evaluation techniques are applied, are those obtained and reported by Castillo, et. al. (2016 & 2020).The error measuring techniques whose calculation yields adequate and convenient results, for the six prediction techniques handled in this article, as long as its interpretation is intuitive, are SMAPE and MAAPE. In this case, the most adequate technique to measure the error presented by the sales prediction system turned out to be SMAPE.

Sales forecast is an indispensable link in the business activities of enterprises, and the accuracy of prediction is directly related to the effectiveness of enterprise sales and operation activities. In order to improve the prediction accuracy, a sales forecasting model based on LSTM is proposed. The model uses SA to optimize the initial connection weights of LSTM neural network, which solves the problem that the LSTM neural network converges to the local optimal, thus improving the network performance, and then makes an empirical analysis of the construction of the sales forecasting model based on SA-LSTM. The results show that the sales forecasting model improves the prediction accuracy, also reduces the number of iterations, and obtains a good prediction effect.