To underscore the critical role of predictive capabilities in third-party logistics (3PL) companies for assortment planning, particularly within the rapidly evolving e-commerce sector and business to business (B2B) flows. This study employs a comprehensive literature review on the forecasting capabilities of 3PL firms, enriched by empirical research across nine logistics facilities. It leverages statistical tools and the ARIMA_PLUS algorithm to evaluate the precision and dependability of demand and supply forecasts generated by these companies. The research reveals that 3PLs possess the ability to generate accurate demand and supply forecasts utilizing advanced forecasting tools. The effectiveness of these forecasts is closely linked to the quality of data available, and the expertise of the personnel involved. Challenges arise in forecasting for smaller order volumes, which are more common in e-commerce flows. The study also highlights that technological advancements and investments in data analytics are pivotal in enhancing forecast accuracy. The investigation focuses on a select group of 3PL companies, potentially limiting the generalizability of the findings. Moreover, the study underscores the necessity for further exploration into how technological innovations impact forecasting capabilities. By emphasizing the significance of 3PL firms' predictive abilities, also for e-commerce assortment planning, this paper addresses a notable gap in existing research. Its insights are invaluable for businesses contemplating logistics outsourcing and for 3PL providers aiming to advance their forecasting proficiency. The findings stress the importance of integrating advanced forecasting models and analytics to stay competitive in the dynamic e-commerce landscape.

In supply chain management, the employed forecasting algorithm plays a very vital and crucial role in how a particular business performs well in the market. This study proposes a time series based forecasting model to help in designing an effective make-to-stock supply chain mechanism for tackling the large number of suppliers (suppliers diversion) and products (items diversion). The proposed technique extends the traditional ARIMA model to ARIMA Double Layering Technique (DLT) where the algorithm is implemented in two layers: first one is to obtain the number of orders level, and the other layer is implemented at the quantity level. The systematic implementation procedure of our approach is illustrated through a real case study. The accuracy evaluation and consistency of the results show that ARIMA -DLT provides superior forecasting when compared with ML-based models which provides insightful managerial views to other similar forecasting problems.

This study aims to determine an accurate forecasting model, especially an error rate of around 0, and to examine how the automatic rejection system reacts to stock price as a result of the pandemic. The statistical clustering method is used for the dataset in form of daily observations, while the sample covers the period of cases before and after COVID-19 pandemic from 02 January 2019 to 20 June 2020 at the Trinitan Minerals and Metal Company. Furthermore, the data used in the estimation are the opening and closing price of returns, which are later processed using SAS analysis tools. It is shown that the most appropriate decision-making processes are those proven to be most effective. Therefore, predicting future events based on a suitable time series model will help policymakers and strategists make decisions and develop appropriate strategic plans regarding the stock market. Meanwhile, 98% of the ARIMA (1,1,1) is a forecasting model which can be applied to predict stock prices. The new approach of this study is an integrated autoregressive moving average used as an attempt to accurately predict stock prices during a pandemic.

This study begins with a literature review to observe current problems surrounding vehicle service centers and the use of the ARIMA method to resolve similar cases. Researchers then conduct the observation process by collecting user needs through surveys and questionnaires. Next, researchers use the Scrum methodology to develop a web-based application enriched with the ARIMA method. Afterward, researchers obtain user feedback using surveys and questionnaires to evaluate the user experience towards the application. Conclusively, based on the results of the questionnaires, the average respondent believes that the web-based application can simplify respondents in making vehicle service reservations with a score of 8.85 out of 10. In addition, the average respondent believes that the web-based application can assist respondents in planning vehicle service. They visit with shorter queue times through a crowded time prediction system on a web-based reservation application with the ARIMA model with a value of 8.9 out of 10.

Business process evaluation is a common norm in small-medium-large industries globally and information obtained during such evaluation have been used in simulating future performance of most industries using mathematical models such as Autoregressive Integrated Moving Average (ARIMA) and artificial neural network (ANN). This study explored the possibility of predicting port productivity and berth effectiveness of seaport using ANN and ARIMA. A comparative analysis of multi-layer perceptron (MLP) back propagation algorithm and ARIMA performance was carried out based on ships days at port, days at berth and tonnage which serves as model inputs, while port productivity and berth effectiveness were the model outputs. The MLP-ANN and ARIMA (1, 0, 4- port productivity) and (1, 0, 4-berth effectiveness) results were compared based on their coefficient of correlation and mean square error. The coefficient of correlation for port productivity prediction using MLP-ANN was 0.998. This value outperformed that of ARIMA (0.9862) for port productivity. The coefficient of correlation of 0.9956 and 0.9928 were obtained for berth effectiveness using MLR and ARIMA, respectively.

The classic ARIMA models use the information criteria for lag selection since 1990s. The information criteria are based on the summation of two expressions: a function of Residual Sum of Squares (RSS) and a penalty for decrease of degrees of freedom. However, the information criteria have some disadvantages since these two expressions do not have the same scale, so the information criteria are mainly based on the first expression (because of its bigger scale). In this paper, we propose a hybrid ARIMA model, which uses the Data Envelopment Analysis (DEA) model to select the best lags of AR and MA process called DEA-ARIMA. DEA is a linear programming technique, which computes a comparative ratio of multiple outputs to multiple inputs for each Decision Making Unit (DMU), which is reported as the relative efficiency score. We identify inputs as the number of AR and MA terms and outputs of the model are inverse of Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE). In fact, in our proposed model, inputs consider as resources, so we are looking for some models with fewer resources and high efficiency. The DEA unlike the information criteria may have more than one solution and all of them are efficient so to compare this two models selection the mean of best DMUs is calculated. Experimental results demonstrate DEA-ARIMA will not trap in over fitting problem in contrast to classic ARIMA models because of considering a set of efficient ARIMA models.