[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-116920-en":3,"doc-seo-116920-105":30,"detail-sidebar-cat-0-en-105":92},{"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":20,"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},116920,549758146520,"Patrick","https://ap-avatar.wpscdn.com/avatar/80002397d8c0411e94?_k=1775819394049821470",8,"Research & Report","OTT Subscriber Churn Prediction Using Machine Learning - May 2023 Project","Subscriber churn is a critical issue for companies relying on recurring revenue from subscription-based services such as OTT platforms. Machine Learning models can predict churn and enable targeted retention strategies for subscribers at risk. The project addresses three research questions: which ML algorithms work for churn prediction, how to predict OTT churn using ML, and how to retain subscribers while improving customer targeting. Using a Kaggle dataset, models are trained and evaluated by accuracy and AUROC, and gradient boosting provides the highest performance. Recommended next steps include using unstructured and real-time data sources and exploring deep learning techniques to improve effectiveness.","California State University, San Bernardino  \nCSUSB ScholarWorks  \n\n| Electronic Theses, Projects, and Dissertations | Office of Graduate Studies |\n| --- | --- |\n| 5-2023\u003Cbr>OTT SUBSCRIBER CHURN PREDICTION USING MACHINE LEARNING\u003Cbr>Needhi Devan Senthil Kumar\u003Cbr>California State University-San Bernardino\u003Cbr>Follow this and additional works at: [https://scholarworks.lib.csusb.edu/etd](https://scholarworks.lib.csusb.edu/etd)\u003Cbr> Part of the Other Computer Engineering Commons |  |\n\nRecommended Citation  \nSenthil Kumar, Needhi Devan, \"OTT SUBSCRIBER CHURN PREDICTION USING MACHINE LEARNING\"(2023) . Electronic Theses, Projects, and Dissertations. 1660.  \n[https://scholarworks.lib.csusb.edu/etd/1660](https://scholarworks.lib.csusb.edu/etd/1660)  \nThis Project is brought to you for free and open access by the Office of Graduate Studies at CSUSB ScholarWorks. It has been accepted for inclusion in Electronic Theses, Projects, and Dissertations by an authorized administrator of CSUSB ScholarWorks. For more information, please contact [scholarworks@csusb.edu](scholarworks@csusb.edu).  \nOTT SUBSCRIBER CHURN PREDICTION  \nUSING MACHINE LEARNING  \nA Project Presented to the Faculty of  \nCalifornia State University, San Bernardino  \nIn Partial Fulfillment of the Requirements for the Degree Master of Science in  \nInformation Systems and Technology  \nby  \nNeedhi Devan Senthil Kumar  \nMay 2023  \nOTT SUBSCRIBER CHURN PREDICTION  \nUSING MACHINE LEARNING  \nA Project Presented to the Faculty of  \nCalifornia State University, San Bernardino  \nby  \nNeedhi Devan Senthil Kumar  \nMay 2023  \nApproved by:  \nDr. William Butler, Member, Committee Chair  \nDr. Conrad Shayo, Member, Reader & Department Chair, Information and  \nDecision Sciences  \n© 2023 Needhi Devan Senthil Kumar  \nABSTRACT  \nSubscriber churn is a critical issue for companies that rely on recurring revenue from subscription-based services like the OTT platform. Machine Learning algorithms can be used to predict churn and develop targeted retention strategies to address the specific needs and concerns of at-risk subscribers. The research questions are 1) What Machine Learning algorithms are used to overcome subscriber churn? 2) How to predict subscribers’ churn in the OTT platform using Machine Learning? 3) How to retain subscribers and improve customer targeting? The dataset was collected from the Kaggle repository and implemented it into the various prediction algorithms used in previous research. Then, evaluate the performance of each algorithm to find out the highest accuracy model. The findings and conclusion for each question are 1) Logistic regression, multi-layer perceptron, random forest, decision trees, and gradient boosting machines were identified as effective algorithms for churn prediction analysis. 2) By sending the test data to a trained model by their historical dataset, customers are likely to leave a company (i.e. , churn) based on their characteristics can be predicted. 3) Personalized offers and promotions, improving customer service, developing loyalty programs, and optimizing pricing strategies were suggested strategies for retaining subscribers. The gradient boosting machine model was found to have the highest accuracy and maximum AUROC, making it a powerful tool in the fight against customer churn. Areas for further study include incorporating unstructured data sources, deep learning  \ntechniques, and integrating real-time data sources to improve the accuracy and effectiveness of churn prediction models.  \nSearch Term: Subscribers, Churn Prediction, OTT Platform  \nACKNOWLEDGEMENTS  \nI would like to thank my parents and my friends for their support and encouragement throughout the process of this project.  \nAlso, I would like to thank Dr. William Butler and Dr. Conrad Shayo for guiding me to finish this project.  \nTABLE OF CONTENTS  \nABSTRACT ................................................................................................. iii  \nACKNOWLEDGEMENTS ............","cbCaimD22CTfodRo","https://ap.wps.com/l/cbCaimD22CTfodRo","pdf",274960,1,33,"English","en",105,"# Abstract\n# Acknowledgements\n# List of Tables\n# List of Figures\n# Chapter One: Introduction\n## Problem Statement\n## Research Questions\n## Organization of the Project\n# Chapter Two: Literature Review\n# Chapter Three: Research Methodology\n## Logistic Regression\n## Multi-Layer Perceptron\n## Random Forest\n## Decision Tree\n## Gradient Boosting Machine\n## Data Collection\n# Chapter Four: Data Description and Analysis\n## System Requirements\n## Implementation\n## Experimental Results\n# Chapter Five: Discussion, Conclusion, and Areas of Further Study\n## Discussion\n## Conclusion\n## Area for Further Study","[{\"question\":\"Which machine learning algorithms were found effective for OTT subscriber churn prediction?\",\"answer\":\"Logistic regression, multi-layer perceptron, random forest, decision trees, and gradient boosting machines were identified as effective algorithms in the study.\"},{\"question\":\"How does the churn prediction approach work using historical data?\",\"answer\":\"The method predicts whether customers are likely to churn by sending test data to models trained on historical characteristics from the dataset.\"},{\"question\":\"What retention strategies were suggested to improve subscriber outcomes?\",\"answer\":\"The project recommends personalized offers and promotions, improving customer service, developing loyalty programs, and optimizing pricing strategies to retain subscribers and improve targeting.\"}]","OTT Subscriber Churn Prediction Using Machine Learning - May 2023 Project | PDF",1785672535,83,{"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":87,"head_meta":89,"extra_data":91,"updated_unix":28},"ott-subscriber-churn-prediction-using-machine-learning-may-2023-project","",{"@graph":36,"@context":86},[37,54,69],{"@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/ott-subscriber-churn-prediction-using-machine-learning-may-2023-project/116920/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05","2026-08-02",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"Which machine learning algorithms were found effective for OTT subscriber churn prediction?","Question",{"text":76,"@type":77},"Logistic regression, multi-layer perceptron, random forest, decision trees, and gradient boosting machines were identified as effective algorithms in the study.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does the churn prediction approach work using historical data?",{"text":81,"@type":77},"The method predicts whether customers are likely to churn by sending test data to models trained on historical characteristics from the dataset.",{"name":83,"@type":74,"acceptedAnswer":84},"What retention strategies were suggested to improve subscriber outcomes?",{"text":85,"@type":77},"The project recommends personalized offers and promotions, improving customer service, developing loyalty programs, and optimizing pricing strategies to retain subscribers and improve targeting.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":46,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":46,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]