Telecom churn case study iiitb

Best-in-class content by leading faculty and industry leaders in the form of videos, cases and projects. Complete all the courses successfully to obtain this prestigious recognition from LJMU. You can choose one of the 5 specialisation, based on your interest.

Learn through real-life industry projects sponsored by top companies across industries. There are 3 simple steps in the Admission Process which is detailed below:. By clicking Start Application, you agree to our terms and conditions and our privacy policy. MBA Global. MBA Executive. Data Science. PG Diploma. Master of Science. PG Certification. View more details.

Machine Learning. Advanced Certification. Digital Marketing. PG Program. Blockchain Technology Management. Executive Program. Master's Degree. Placement track in FullStack Development. Placement Track.Helping organizations engage people and uncover insight from data to shape the products, services and experiences they offer. Please visit the COVID response page for resources and advice on managing through the crisis today and beyond.

Type in a topic service or offering and then hit Enter to search. But when the analytical models confuse more than they clarify, changes need to be made. For one U. We also helped the company uncover other important customer service enhancements by analyzing the text data customers enter during their interactions. This information also revealed ways the telecom could increase both first call and first ticket resolutions. We developed a sentiment score to identify trending reasons for customer satisfaction and displeasure.

Based on customer surveys, this analysis helps the telecom focus on real impacts to customer satisfaction. Addressing high-risk customers is just one way data can improve customer satisfaction. Type in a topic service or offering and then hit Enter to search Common Searches :. Your information has been submitted successfully!

Listening to the Voice of the Customer Reduces Churn Addressing high-risk customers is just one way data can improve customer satisfaction.Best-in-class content by leading faculty and industry leaders in the form of videos, cases and projects.

Become a part of the vast upGrad alumni community post completion of the program. Learn through real-life industry projects sponsored by top companies across industries. By clicking Submit Application, you agree to our terms and conditions and our privacy policy.

MBA Global. MBA Executive. Data Science. PG Diploma. Master of Science. PG Certification. View more details. Machine Learning. Advanced Certification. Digital Marketing. PG Program. Blockchain Technology Management.

Customer churn prediction in telecom using machine learning in big data platform

Executive Program. Master's Degree. Placement track in FullStack Development. Placement Track. Software Development - Blockchain. Fundamentals of Programming. Request Callback. Placement Support. For Business. Upskill Own a Franchise Hire from upGrad. With Industry Experts From. Jun 29, Program Overview Key Highlights. Bachelor's Degree, No minimum work experience required. Download Syllabus. Programming Languages and Tools Covered. Instructors Learn from India's leading Deep Learning faculty and industry leaders.

Chandrashekar has a Ph. Anjali has a Ph. Her research interests include computer and wireless networks. An alumnus of McKinsey and Co. He has an M. He has a Ph.Lead the AI-driven technological revolution by upskilling yourself in cutting-edge concepts and applications of Machine Learning and Artificial Intelligence.

This program will help you:. Participate in hackathons and develop a portfolio of industry projects. Following are some of the USPs of the program:. These projects are created in close collaboration with industry experts to help you develop an in-depth understanding of industry trends. You will get industry mentorship which will help you prepare for the roles of tomorrow.

The key areas of focus will be:. Course 0 - Pre Program Preparation. Course 1 - Statistics and Exploratory Data Analytics. Course 2 - Machine Learning 1. Course 3 - Machine Learning 2. Course 4 - Natural Language Processing. Course 6 - Reinforcement Learning. This a industry-relevant yet academically-rigorous 12 month program covering Machine Learning and AI concepts.

This is not a program for professionals to transition to entry level data science positions.

telecom churn case study iiitb

This program is designed for working professionals looking to pick up skills in advanced concepts like Reinforcement Learning, Graphical Models, NLP, Deep Learning along with a solid foundation of Statistics.

This program demands consistent work and time commitment over the entire duration of 11 months. The content will be largely asynchronous, consisting of interactive lectures from industry leaders and world-renowned faculty. Additionally, the program comprises live lectures and hangout sessions dedicated to solving your academic queries and reinforcing learning.

Hence we want to make sure that the participants of this program also show a very high level of commitment and passion towards Machine Learning and AI.

PG Diploma - Data Science

The applicants will have to take a selection test designed to check their mathematical and programming abilities. How do I know if this program is for me? This program is for you if you are a: Data Scientist or Senior Data Analyst : If you are comfortable with data wrangling, have implemented statistical or machine learning models in past and have spent at least 2 years as a working professional.

Statistician : If you received formal education in statistics or mathematics and have at least 2 years of working experience. In addition, you should be familiar with various frameworks and tools like Hadoop and Spark. How will this program benefit me? The program will benefit you in different ways depending upon your prior experience: Data Scientist or Senior Data Analyst: The program will familiarize you with advancements in ML and AI.

It will also help you understand the mathematics behind algorithms and how you can modify them to suit your needs so that you can transition to a Senior Data Science or Machine Learning role. It will build upon your existing knowledge of various tools to make you a full stack Machine Learning or Data Science professional. Software Developers: The program will help you create a strong foundation of statistics, machine learning and business understanding. It will leverage your existing knowledge of programming and expand the technologies you are familiar with so that you can become a well-rounded Machine Learning professional.Accelerate your career in data science by mastering concepts of Analytics, Statistics, Machine Learning and Big Data from the most influential analytics leaders and academicians of India.

PG Diploma - Machine Learning & Artificial Intelligence

The month online PG Diploma in Data Science, co-developed by IIIT Bangalore and powered by upGrad, covers the depth and breadth of the subject in the form of interactive lectures, live sessions and hands-on industry projects.

The program offers a right blend of statistics, technical and business knowledge. The curriculum has been designed with multiple industry leaders to ensure that you learn exactly what the employers need. The key areas of focus will be:. Course II - Machine Learning: Understand the relevance and power of prediction across industry verticals.

By the end of the course, you will have an actionable knowledge of different machine learning algorithms and their applications.

Post Course II, choose from 1 of the 5 specialisations offered as per your background and career aspirations:. The PG Diploma is an engaging, yet rigorous, month online program designed specifically for working professionals to develop practical knowledge and skills, establish a professional network and accelerate entry into data science careers.

Expect to carry out several industry-relevant projects simulated as per the actual workplace, making you a skilled data science professional at par with leading industry standards. The program is NOT going to be easy. It will require at least hours of your time commitment per week to apply new concepts and execute industry relevant projects.

What topics are going to be covered as part of the program? The program is designed for working professionals looking for a transition into the data domain. Considering the requirements of different data roles in the industry, the curriculum is divided into five tracks. These five tracks will have a common curriculum running for approximately months that every student will go through after which they have to do two specialization courses and a capstone project in the remaining months.

Can I sign up only for a few specific modules if I am interested? No, the program is designed to be completed in its entirety, and cannot be taken as standalone modules. What type of learning experience should I expect? The content will be largely asynchronous, comprising of interactive lectures from industry leaders and world-renowned faculty.

Additionally, the program comprises of live lectures and hangout sessions dedicated to solving your academic queries and reinforcing learning. What is the time commitment expected for the program? At least hours per week of time commitment is expected to be able to graduate from the program. Is there any certification granted at the end of the program?Metrics details.

Customer churn is a major problem and one of the most important concerns for large companies. Due to the direct effect on the revenues of the companies, especially in the telecom field, companies are seeking to develop means to predict potential customer to churn.

Therefore, finding factors that increase customer churn is important to take necessary actions to reduce this churn. The main contribution of our work is to develop a churn prediction model which assists telecom operators to predict customers who are most likely subject to churn.

Another main contribution is to use customer social network in the prediction model by extracting Social Network Analysis SNA features. The use of SNA enhanced the performance of the model from 84 to The model was prepared and tested through Spark environment by working on a large dataset created by transforming big raw data provided by SyriaTel telecom company.

This algorithm was used for classification in this churn predictive model. The telecommunications sector has become one of the main industries in developed countries. The technical progress and the increasing number of operators raised the level of competition [ 1 ]. Companies are working hard to survive in this competitive market depending on multiple strategies.

Three main strategies have been proposed to generate more revenues [ 2 ]: 1 acquire new customers, 2 upsell the existing customers, and 3 increase the retention period of customers. However, comparing these strategies taking the value of return on investment RoI of each into account has shown that the third strategy is the most profitable strategy [ 2 ], proves that retaining an existing customer costs much lower than acquiring a new one [ 3 ], in addition to being considered much easier than the upselling strategy [ 4 ].

On the other hand, predicting the customers who are likely to leave the company will represent potentially large additional revenue source if it is done in the early phase [ 3 ]. Many research confirmed that machine learning technology is highly efficient to predict this situation.

This technique is applied through learning from previous data [ 67 ]. The data also comes very fast and needs a suitable big data platform to handle it.

The dataset is aggregated to extract features for each customer. SNA features made good enhancement in AUC results and that is due to the contribution of these features in giving more different information about the customers. We focused on evaluating and analyzing the performance of a set of tree-based machine learning methods and algorithms for predicting churn in telecommunications companies.

We have experimented a number of algorithms such as Decision Tree, Random Forest, Gradient Boost Machine Tree and XGBoost tree to build the predictive model of customer Churn after developing our data preparation, feature engineering, and feature selection methods. SyriaTel company was interested in this field of study because acquiring a new customer costs six times higher than the cost of retaining the customer likely to churn. We experimented three scenarios to deal with the unbalance problem which are oversampling, undersampling and without re-balancing.

Data Mining techniques were applied on top of the Data Warehouse system, but the model failed to give high results using this data. The Data Warehouse was not able to acquire, store, and process that huge amount of data at the same time.

telecom churn case study iiitb

The computational complexity of SNA measures is very high due to the nature of the iterative calculations done on a big scale graph, as mentioned in Eqs.

Big data system allowed SyriaTel Company to collect, store, process, aggregate the data easily regardless of its volume, variety, and complexity. We believe that big data facilitated the process of feature engineering which is one of the most difficult and complex processes in building predictive models.

By using the big data platform, we give the power to SyriaTel company to go farther with big data sources. The model also was evaluated using a new dataset and the impact of this system to the decision to churn was tested.

The model gave good results and was deployed to production.Currently they have been Focusing on retaining their customers on a reactive basis when the subscriber calls in to close the account by targeted proactive retention programs, which include usage enhancing marketing programs to increase minutes of usage,migration of plans, and a bundling strategy.

Retention drivers vary by market maturity, delivering excellent quality keeps customer happy and loyal. Among the problems they report are slow download speeds. Another key finding of Acquisition and Retention Survey Report is that recommendations from family and friends have gained in importance in the decision to switch operators. Subscribers who have switched operators in recent months reported two key information success in their decision. Skip to content. The Problem is to discuss a survey report where the Mobicom management team was concerned that the market environment of rising churn rates will hit them even harder as churn rate at Mobicom is relatively high.

The Acquistion and Retention Survey Report Retention drivers vary by market maturity, delivering excellent quality keeps customer happy and loyal. The Challenge To be able to effectively drive these retention strategies, a few key questions requires urgent attention What the top five factors driving likelihood of churn at Mobicom.

Recommend rate plan migration as a proactive strategy and how to prioritization customer for a proactive retention campaigns in the future.

Final Presentation Customer Churn in Telecom Industry

The Decision We use R-programming the most widely used language and tool for machine learning and statistical computing to derive a model that can answer the solution.

The Data Source Consists of 80, rows of data with 27 indicators. Our Deployment Strategy Data Aggregation: We use various sources of data to complied into one meaningful data set. Data Cleaning: We go through regorious sanity check to impute the missing values, outliers to compile it one meaningful dataset. Transformation: using complex machine learning techniques we create a model that results in answering all the solutions The Machine Learning Model A Comprehensive Machine Learning Model The Solution using the Machine Learning Model, we are able to figure out the top factors driving likelihood of churn.

About the Program

And recommended a rate plan migration as a proactive strategy. Further recommend the following points to prioritize from the churn model for a proactive retention campaigns in the future : Not to have Drop voice calls which leads to churn and also need to improve data connectivity problems which also plays an important part in retention of customers.

Now this is what we call as Data2Zodiac.

telecom churn case study iiitb

Share this: Twitter Facebook. Like this: Like Loading Menu Home Case Studies Contact. Facebook LinkedIn Twitter Instagram. Post to Cancel. By continuing to use this website, you agree to their use. To find out more, including how to control cookies, see here: Cookie Policy.


comments

Leave a Reply

Your email address will not be published. Required fields are marked *