[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119519-en":3,"doc-seo-119519-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},119519,13056703019662,"Evangeline","https://ap-avatar.wpscdn.com/avatar/be000253a8e92610077?_k=1778726343310543188",8,"Research & Report","Hybrid Approaches to Machine Learning for Improved Battery Sales Forecasting - A Case Study in Thailand","Battery sales forecasting is critical for demand planning in the automotive battery industry because it shapes production plans, inventory control, and supply chain optimization. This case study evaluates traditional forecasting models and machine learning methods to predict monthly battery sales for Thailand’s top-selling products from January 2018 to December 2023. Holt, Holt-Winters, ARIMA, SARIMA, and SARIMAX are compared with LSTM and ANN, including hybrid combinations that exploit complementary strengths. External variables and lagged data are integrated during feature selection and performance is assessed using MAPE, with the ANN-LSTM hybrid achieving the best results at 8.83% average MAPE.","Article  \nHybrid Approaches to Machine Learning for Improved Battery Sales Forecasting:  \nA Case Study in Thailand  \nSanti Wongkamphua and Naragain Phumchusrib,*  \nDepartment of Industrial Engineering, Faculty of Engineering, Chulalongkorn University, Bangkok 10330, Thailand  \n[E-mail:](E-mail: a 6570258821@alumni.chula.ac.th)[ a](E-mail: a 6570258821@alumni.chula.ac.th)[ 6570258821@alumni.chula.ac.th](E-mail: a 6570258821@alumni.chula.ac.th), b,*[naragain.p@chula.ac.th](naragain.p@chula.ac.th) (Corresponding author)  \nAbstract. Battery sales forecasting is a critical component of demand planning in the automotive battery industry, directly influencing production, inventory management, and supply chain optimization. This study presents a comprehensive evaluation of traditional forecasting methods and machine learning techniques to predict monthly sales for a battery manufacturer in Thailand. Utilizing a dataset of monthly sales for the 10 best-selling products from January 2018 to December 2023, the research investigates the performance of traditional models such as Holt’s Linear Trend, Holt-Winters Seasonal, ARIMA, SARIMA, and SARIMAX. Advanced machine learning approaches, including Long ShortTerm Memory (LSTM) networks and Artificial Neural Networks (ANN), are also explored. Additionally, hybrid models combining traditional and machine learning techniques are developed to leverage their respective strengths. The study integrates external factors such as economic indicators, industry-specific variables, and lagged data during feature selection to enhance predictive accuracy. Model performance is rigorously evaluated using Mean Absolute Percentage Error (MAPE) . The results demonstrate that the hybrid ANN-LSTM model achieves the highest accuracy, with an average MAPE of 8.83%, significantly outperforming individual models, including the best-performing traditional model, ANN, at 9.43%. This research contributes to the field by providing a robust analytics framework that integrates traditional and advanced machine learning methodologies, offering actionable insights for battery sales forecasting and enhancing decision-making processes in the automotive industry.  \nKeywords: hybrid machine learning, battery sales forecasting, traditional forecasting methods, machine learning techniques.  \nENGINEERING JOURNAL Volume 29 Issue 2 Received 21 August 2024  \nAccepted 29 January 2025 Published 28 February 2025 Online at [https://engj.org/](https://engj.org/)  \n[DOI:10.4186/ej.2025.29.2.27](DOI:10.4186/ej.2025.29.2.27)  \n1. Introduction  \nThe battery industry is a cornerstone of modern technology, powering everything from consumer electronics to automotive vehicles and industrial machinery. Among the various types of batteries, lead-acid batteries have been a stalwart, primarily due to their reliability, recyclability, and cost-efficiency. Despite the rising interest in electric vehicles (EVs) and associated battery technologies like lithium-ion, lead-acid batteries remain indispensable for conventional automotive applications, including starting, lighting, and ignition (SLI) systems in vehicles [1] .  \nThailand has become a pivotal player in the global automotive market, establishing itself as a significant manufacturing and export hub within Southeast Asia. This is clearly illustrated in Fig. 1., which depicts the Domestic Automotive Sales in Thailand from 2014 to 2023. As the graph shows, the country's lead-acid battery market has flourished alongside a vigorous automotive sector, which extensively utilizes these batteries for diverse applications ranging from vehicles to renewable energy storage systems [2] . The strategic emphasis on automotive production and exportation has not only carved a niche for Thailand as a prime location for battery manufacturing but has also drawn investments from international corporations, thereby nurturing a dynamic and competitive local industry [3] .  \nFig. 1. Domestic automotive sales in Thailand fr","cbCaigY4kOFxXBZv","https://ap.wps.com/l/cbCaigY4kOFxXBZv","pdf",1998388,1,17,"English","en",105,"# Introduction\n## Battery sales forecasting and demand planning\n## Forecasting methods across industries\n## Lead-acid batteries and the Thai automotive market","[{\"question\":\"What forecasting problem does the study address?\",\"answer\":\"It focuses on predicting monthly battery sales to support demand planning, production scheduling, inventory management, and supply chain decisions in Thailand’s automotive battery industry.\"},{\"question\":\"Which traditional and machine learning models are evaluated?\",\"answer\":\"The study tests Holt’s Linear Trend, Holt-Winters Seasonal, ARIMA, SARIMA, and SARIMAX, alongside machine learning models including LSTM networks and Artificial Neural Networks (ANN).\"},{\"question\":\"How do hybrid models affect forecasting accuracy?\",\"answer\":\"Hybrid models combining traditional forecasting with machine learning aim to leverage each approach’s strengths. The results show the ANN-LSTM hybrid achieves the highest accuracy with the lowest average MAPE of 8.83%.\"}]","Hybrid Approaches to Machine Learning for Improved Battery Sales Forecasting - A Case Study in Thailand | PDF",1785724748,43,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"hybrid-approaches-to-machine-learning-for-improved-battery-sales-forecasting-a-case-study-in-thailand","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/hybrid-approaches-to-machine-learning-for-improved-battery-sales-forecasting-a-case-study-in-thailand/119519/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What forecasting problem does the study address?","Question",{"text":75,"@type":76},"It focuses on predicting monthly battery sales to support demand planning, production scheduling, inventory management, and supply chain decisions in Thailand’s automotive battery industry.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which traditional and machine learning models are evaluated?",{"text":80,"@type":76},"The study tests Holt’s Linear Trend, Holt-Winters Seasonal, ARIMA, SARIMA, and SARIMAX, alongside machine learning models including LSTM networks and Artificial Neural Networks (ANN).",{"name":82,"@type":73,"acceptedAnswer":83},"How do hybrid models affect forecasting accuracy?",{"text":84,"@type":76},"Hybrid models combining traditional forecasting with machine learning aim to leverage each approach’s strengths. The results show the ANN-LSTM hybrid achieves the highest accuracy with the lowest average MAPE of 8.83%.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]