Machine learning approach for complaint prediction in the telecom industry / (Record no. 172856)
[ view plain ]
| 000 -LEADER | |
|---|---|
| fixed length control field | 07082namaa22004091i 4500 |
| 003 - CONTROL NUMBER IDENTIFIER | |
| control field | OSt |
| 005 - أخر تعامل مع التسجيلة | |
| control field | 20250811102849.0 |
| 008 - FIXED-LENGTH DATA ELEMENTS--GENERAL INFORMATION | |
| fixed length control field | 250701s2024 ua a|||frm||| 000 0 eng d |
| 040 ## - CATALOGING SOURCE | |
| Original cataloguing agency | EG-GICUC |
| Language of cataloging | eng |
| Transcribing agency | EG-GICUC |
| Modifying agency | EG-GICUC |
| Description conventions | rda |
| 041 0# - LANGUAGE CODE | |
| Language code of text/sound track or separate title | eng |
| Language code of summary or abstract | eng |
| -- | ara |
| 049 ## - Acquisition Source | |
| Acquisition Source | Deposit |
| 082 04 - DEWEY DECIMAL CLASSIFICATION NUMBER | |
| Classification number | 005.7 |
| 092 ## - LOCALLY ASSIGNED DEWEY CALL NUMBER (OCLC) | |
| Classification number | 005.7 |
| Edition number | 21 |
| 097 ## - Degree | |
| Degree | M.Sc |
| 099 ## - LOCAL FREE-TEXT CALL NUMBER (OCLC) | |
| Local Call Number | Cai01.18.11.M.Sc.2024.Mo.M |
| 100 0# - MAIN ENTRY--PERSONAL NAME | |
| Authority record control number or standard number | Mohamed Mahmoud Mahnie Gewaly, |
| Preparation | preparation. |
| 245 10 - TITLE STATEMENT | |
| Title | Machine learning approach for complaint prediction in the telecom industry / |
| Statement of responsibility, etc. | by Mohamed Mahmoud Mahnie Gewaly ; Supervised by Prof. Dr. Ammar Mohammed Ammar Mohammed. |
| 246 15 - VARYING FORM OF TITLE | |
| Title proper/short title | نهج التعلم الآلي للتنبؤ بالشكاوى في صناعة الاتصالات |
| 264 #0 - PRODUCTION, PUBLICATION, DISTRIBUTION, MANUFACTURE, AND COPYRIGHT NOTICE | |
| Date of production, publication, distribution, manufacture, or copyright notice | 2024. |
| 300 ## - PHYSICAL DESCRIPTION | |
| Extent | 116 Leaves : |
| Other physical details | illustrations ; |
| Dimensions | 30 cm. + |
| Accompanying material | CD. |
| 336 ## - CONTENT TYPE | |
| Content type term | text |
| Source | rda content |
| 337 ## - MEDIA TYPE | |
| Media type term | Unmediated |
| Source | rdamedia |
| 338 ## - CARRIER TYPE | |
| Carrier type term | volume |
| Source | rdacarrier |
| 502 ## - DISSERTATION NOTE | |
| Dissertation note | Thesis (M.Sc)-Cairo University, 2024. |
| 504 ## - BIBLIOGRAPHY, ETC. NOTE | |
| Bibliography, etc. note | Bibliography: pages 112-115. |
| 520 #3 - SUMMARY, ETC. | |
| Summary, etc. | The quality of service (QoS) provided to individual telecommunications customers is a critical element affecting their satisfaction levels. This study recommends a predictive model to forecast customer complaints before they escalate, therefore optimizing resource allocation and enhancing customer satisfaction. The main goal is on fixed broadband services provided by a top Egyptian mobile network operator.<br/>Using a real-world dataset comprising 100,000 customers and 12 features, I used a collection of machine learning models. These models use historical and real-time customer data including service logs and previous complaints, to find patterns indicative of future complaints. Classification algorithms such as Random Forest, AdaBoost with Decision Tree, Logistic Regression, K-Nearest Neighbors, Gaussian Naive Bayes, Decision Tree and Support Vector Machine were used to analyze the data and extract very important information.<br/>The AdaBoost with Decision Tree model showed excellent performance across various evaluation metrics, including accuracy, precision, recall and F1-score. The AdaBoost classifier with Decision Trees performed the best among the models tested with accuracy scores of 0.96, respectively to accurately predict customer complaints. This model effectively classified customers based on their likelihood of raising future complaints because its simplicity of use and ability to capture nonlinear relationships as their capacity to manage intricate decision boundaries fits in effectively with the complex patterns found in the dataset.<br/>The results of this study offer valuable information for telecommunications service providers seeking to improve customer experience and reduce churn. By identifying possible problems ahead of time and taking action, operators can make the most of their resources, cut down on expenses and build stronger customer loyalty. Using data-driven strategies has become necessary in a competitive world, as it helps businesses make smart decisions, simplify processes and predict possible results. Putting this model into practice provides a solid approach for using predictive analytics into daily operations, allowing companies to act on insights and improve efficiency. By focusing on customer behavior and service interaction patterns, the predictive model allows for early interventions, ensuring that customers’ issues are resolved before they become formal complaints. This not only enhances customer satisfaction but also enables more efficient utilization of technical support teams, reducing the need for reactive measures and improving overall service delivery.<br/>In addition, the study highlights the greater effects of machine learning in enhancing customer satisfaction strategies across the telecommunications industry. The ability to predict complaints serves as a foundation for personalized service delivery via which customers’ needs are forecasted and addressed in real-time. The approach presented in this research displays how predictive analytics can be used to maintain competitiveness in a quickly changing market, positioning operators to deliver excellent service while maintaining cost efficiency. |
| 520 #3 - SUMMARY, ETC. | |
| Summary, etc. | إن جودة الخدمة المقدمة لعملاء الاتصالات الفردية هي عامل أساسي يؤثر على رضاهم. تقترح هذه الدراسة نموذجًا تنبؤيًا لتوقع شكاوى العملاء قبل تفاقمها، وبالتالي تحسين تخصيص الموارد وتعزيز رضا العملاء. ويركز هذا على خدمات الانترنت الارضى التي تقدمها شركة رائدة في مجال تشغيل شبكات الهاتف المحمول في مصر.<br/>باستخدام مجموعة بيانات واقعية تضم 100000 عميل و12 ميزة، قمنا بتطوير مجموعة من نماذج التعلم الآلي. تستفيد هذه النماذج من بيانات العملاء التاريخية والحقيقية، بما في ذلك سجلات الخدمة والشكاوى السابقة، لتحديد الأنماط التي تشير إلى الشكاوى المحتملة. تم استخدام خوارزميات التصنيف مثل Random Forest وAdaBoost with Decision Tree وLogistic Regression وK-Nearest Neighbors و Gaussian Naive Bayes و Decision Tree وSupport Vector Machine لتحليل البيانات واستخراج رؤى ذات مغزى.<br/>أظهر نموذج AdaBoost with Decision Tree أداءً متفوقًا عبر مقاييس التقييم المختلفة، بما في ذلك الدقة والدقة والتذكر ودرجة F1. لقد نجح هذا النموذج في تصنيف العملاء بشكل فعال على أساس احتمالية تقديمهم لشكاوى مستقبلية.<br/>إن نتائج هذه الدراسة تقدم إرشادات قيمة لمقدمي خدمات الاتصالات الذين يسعون إلى تحسين تجربة العملاء والحد من فقدان العملاء. ومن خلال تحديد المشكلات المحتملة ومعالجتها بشكل استباقي، يمكن للمشغلين تحسين تخصيص الموارد وتقليل التكاليف وتعزيز ولاء العملاء. إن تطبيق الاستراتيجيات القائمة على البيانات أمر ضروري في ظل المنافسة الحالية. |
| 530 ## - ADDITIONAL PHYSICAL FORM AVAILABLE NOTE | |
| Issues CD | Issues also as CD. |
| 546 ## - LANGUAGE NOTE | |
| Text Language | Text in English and abstract in Arabic & English. |
| 650 #0 - SUBJECT ADDED ENTRY--TOPICAL TERM | |
| Topical term or geographic name entry element | Data Science |
| 653 #1 - INDEX TERM--UNCONTROLLED | |
| Uncontrolled term | Machine Learning |
| -- | Telecom |
| -- | Internet |
| -- | Fixed Broadband |
| -- | Classification |
| -- | Complaint Prediction |
| -- | Data Analysis |
| 700 0# - ADDED ENTRY--PERSONAL NAME | |
| Personal name | Ammar Mohammed Ammar Mohammed |
| Relator term | thesis advisor. |
| 900 ## - Thesis Information | |
| Grant date | 01-01-2024 |
| Supervisory body | Ammar Mohammed Ammar Mohammed |
| Universities | Cairo University |
| Faculties | Faculty of Graduate Studies for Statistical Research |
| Department | Department of Data Science |
| 905 ## - Cataloger and Reviser Names | |
| Cataloger Name | Shimaa |
| Reviser Names | Eman Ghareb |
| 942 ## - ADDED ENTRY ELEMENTS (KOHA) | |
| Source of classification or shelving scheme | Dewey Decimal Classification |
| Koha item type | Thesis |
| Edition | 21 |
| Suppress in OPAC | No |
| Source of classification or shelving scheme | Home library | Current library | Date acquired | Inventory number | Full call number | Barcode | Date last seen | Effective from | Koha item type |
|---|---|---|---|---|---|---|---|---|---|
| Dewey Decimal Classification | المكتبة المركزبة الجديدة - جامعة القاهرة | قاعة الرسائل الجامعية - الدور الاول | 01.07.2025 | 91719 | Cai01.18.11.M.Sc.2024.Mo.M | 01010110091719000 | 01.07.2025 | 01.07.2025 | Thesis |