Accurate sales forecasting is essential for stakeholders to make strategic decisions. This study aims to compare the performance of two deep learning models, namely Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN), in forecasting domestic motorcycle sales produced by AISI member manufacturers. The forecast is based on historical data from January 2021 to December 2024. The model was trained using time series data and the forecasting results for the period January to March 2025 were evaluated using the metrics Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and Mean Absolute Percentage Error (MAPE). The results show that the LSTM model produces lower MAE and MAPE values than CNN, which shows its superiority in providing more accurate and consistent predictions. On the other hand, the CNN model has lower RMSE and MSE values, thus being able to reduce large prediction errors. By comparing the results of LSTM, CNN, and actual data forecasting, the LSTM model is more suitable for forecasting motorcycle sales in Indonesia

XYZ is a company engaged in the metal casting and machining industry, playing a role as a company that produces products and markets its products in various regions. The formulation of marketing strategy analysis needs to be carried out in this research so that it can compete more with other competitors. While SWOT is an analytical method that is widely used to determine strategic factors, which are based on strengths, weaknesses, opportunities and threats, owned by a company. But in fact the SWOT method raises many alternative strategies, making it less efficient in determining the marketing strategy decisions to be used. Therefore, the Analytical Hierarchy Process (AHP) method is needed, with this method you can choose the best alternative based on information on the most preferred alternative. Because this method can focus on a problem to be solved and can be framed in a more organized frame of mind, so that decision making can be more effective on existing problems, namely Strength Opportunity (SO), Weakness Opportunity (WO), Strength Threats (ST), Weakness Threats (WT). The determination of the AHP method produces Weakness Threats (WT) with the highest weight of 5.61 as the strategy chosen to be applied to PT. XYZ, namely, always continue to innovate in utilizing technology properly, especially in marketing management so that the product promotion process can be maximized, then by continuing to be active in promoting so as not to lose competitiveness with the popularity of other competitors.

The sawmill machine is one of the machines highly used in the cutting process n furniture production at PT X. The sawmill machine used at PT X experiences various problems, including damage and damage repair time in more than 15% of the total production time. The event of machine failures also causes several impacts, such as low target achievement and non-uniform quality. The Overall Equipment Effectiveness (OEE) gets an average OEE value for the period January 2021 - June 2021 of 46.79%, which is still far from the ideal standard value of Overall Equipment Effectiveness, which is 85%. Factors that greatly influence the low value of OEE based on. The sixth significant losses analysis is rework losses of 17.48%, followed by breakdown losses and reduced speed losses, which both have a percentage of 16.12%. Meanwhile, for Set up and Adjustment Loss, Idling Minor Stoppage, and Scrap or Yield Loss, the portions are relatively small, less than 5%.

Technology developments in the era of the industrial revolution 4.0 provide many opportunities to improve supply chain performance and performance. The existence of the waste processing industry as a business has prospects for development, given the large amount of waste generated by the community and the need for several processed products. PT A reduced the amount of garbage that accumulates in the final disposal site (TPA) by reprocessing the waste produced by the community. The existence of waste banks, government agencies, hotels, zoos, and Islamic boarding schools is one of the sources of waste that is processed for waste products. This paper seeks to develop the concept of a digital supply chain by adopting the supply chain model run by PT A. The initial identification presented in this paper can result in several technology identifications that need to be prioritized in implementing relevant technologies in the industry. The expected impact of this implementation is an increase in supply chain performance

Material handling in the production division of publisher X encountered several obstacles, including the transfer of material between production processes having cross-movement flows. This condition occurs as a result of an irregular engine layout. The impact of the conditions in the transfer of material in the production process is the distance of the transfer to be 968.6 m/day. This condition causes some machines to be repositioned, so that material transfer can run faster and more efficiently. One of the efforts to reduce material transfer is to re-plan the placement of production facilities by adopting the concept of a cellular manufacturing system or cellular manufacturing system that is feasible to be applied to the production process of publisher X. The cellular manufacturing system was chosen because it is in accordance with the number of characteristics of the publishing industry that requires the ability to anticipate changes. This rapid demand suits a particular market. This article describes how the results of rearranging and minimizing the distance of moving raw materials in the production section of publisher X by adopting the concept of a cellular manufacturing system and rearranging the layout of production facilities by using sorting using Sorting Algorithms. The selection of the Sorting Algorithms is based on consideration of the order of the output which is not coherent, so it needs to be sorted. Efficient sorting is needed to determine the part-machine incidence matrix which is then used in the development of cellular manufacturing systems. Program development on Visual Studio 2012 software shows the results of facility layout planning by grouping 20 machines and 11 products with this layout change, the total material handling distance is reduced by 371.8 m or by 61.61%