Sunday, May 19, 2024
Top Selling Multipurpose WP Theme

The telecommunications trade is extra aggressive than ever earlier than. With prospects capable of simply change between suppliers, decreasing buyer churn is a vital precedence for telecom corporations who need to keep forward. To deal with this problem, Dialog Axiata has pioneered a cutting-edge answer known as the Dwelling Broadband (HBB) Churn Prediction Mannequin.

This publish explores the intricacies of Dialog Axiata’s strategy, from the meticulous creation of almost 100 options throughout ­10 distinct areas and the implementation of two important fashions utilizing Amazon SageMaker:

  • A base mannequin powered by CatBoost, an open supply implementation of the Gradient Boosting Choice Tree (GBDT) algorithm
  • An ensemble mannequin, benefiting from the strengths of a number of machine studying (ML) fashions

About Dialog Axiata

Dialog Axiata PLC (a part of the Axiata Group Berhad) is considered one of Sri Lanka’s largest quad-play telecommunications service suppliers and the nation’s largest cell community operator with 17.1 million subscribers, which quantities to 57% of the Sri Lankan cell market. Dialog Axiata offers quite a lot of providers, resembling fixed-line, home broadband, cell, tv, fee apps, and monetary providers in Sri Lanka.

In 2022, Dialog Axiata made important progress of their digital transformation efforts, with AWS enjoying a key function on this journey. They centered on bettering customer support utilizing knowledge with synthetic intelligence (AI) and ML and noticed constructive outcomes, with their Group AI Maturity growing from 50% to 80%, in accordance with the TM Discussion board’s AI Maturity Index.

Dialog Axiata runs a few of their business-critical telecom workloads on AWS, together with Charging Gateway, Fee Gateway, Marketing campaign Administration System, SuperApp, and numerous analytics duties. They use number of AWS providers, resembling Amazon Elastic Compute Cloud (Amazon EC2) and Amazon Elastic Kubernetes Service (Amazon EKS) for computing, Amazon Relational Database Service (Amazon RDS) for databases, Amazon Easy Storage Service (Amazon S3) for object storage, Amazon OpenSearch Service for search and analytics, SageMaker for ML, and AWS Glue for knowledge integration. This strategic use of AWS providers delivers effectivity and scalability of their operations, in addition to the implementation of superior AI/ML functions.

For extra about how Axiata makes use of AWS providers, see Axiata Selects AWS as its Primary Cloud Provider to Drive Innovation in the Telecom Industry

Challenges with understanding buyer churn

The Sri Lankan telecom market has excessive churn charges resulting from a number of components. A number of cell operators present related providers, making it simple for patrons to change between suppliers. Pay as you go providers dominate the market, and multi-SIM utilization is widespread. These circumstances result in an absence of buyer loyalty and excessive churn charges.

Along with its core enterprise of cell telephony, Dialog Axiata additionally provides various providers, together with broadband connections and Dialog TV. Nonetheless, buyer churn is a typical concern within the telecom trade. Due to this fact, Dialog Axiata wants to search out methods to cut back their churn charge and retain extra of their present dwelling broadband prospects. Potential options may contain bettering buyer satisfaction, enhancing worth propositions, analyzing causes for churn, or implementing buyer retention initiatives. The hot button is for Dialog Axiata to achieve insights into why prospects are leaving and take significant actions to extend buyer loyalty and satisfaction.

Resolution overview

To cut back buyer churn, Dialog Axiata used SageMaker to construct a predictive mannequin that assigns every buyer a churn threat rating. The mannequin was educated on demographic, community utilization, and community outage knowledge from throughout the group. By predicting churn 45 days prematurely, Dialog Axiata is ready to proactively retain prospects and considerably cut back buyer churn.

Dialog Axiata’s churn prediction strategy is constructed on a sturdy structure involving two distinct pipelines: one devoted to coaching the fashions, and the opposite for inference or making predictions. The coaching pipeline is accountable for growing the bottom mannequin, which is a CatBoost mannequin educated on a complete set of options. To additional improve the predictive capabilities, an ensemble mannequin can be educated to determine potential churn cases which will have been missed by the bottom mannequin. This ensemble mannequin is designed to seize extra insights and patterns that the bottom mannequin alone could not have successfully captured.

The mixing of the ensemble mannequin alongside the bottom mannequin creates a synergistic impact, leading to a extra complete and correct inference course of. By combining the strengths of each fashions, Dialog Axiata’s churn prediction system good points an enhanced general predictive functionality, offering a extra strong and dependable identification of consumers prone to churning.

Each the coaching and inference pipelines are run 3 times per thirty days, aligning with Dialog Axiata’s billing cycle. This common schedule makes certain that the fashions are educated and up to date with the newest buyer knowledge, enabling well timed and correct churn predictions.

Within the coaching course of, options are sourced from Amazon SageMaker Characteristic Retailer, which homes almost 100 fastidiously curated options. As a result of real-time inference will not be a requirement for this particular use case, an offline function retailer is used to retailer and retrieve the required options effectively. This strategy permits for batch inference, considerably decreasing each day bills to below $0.50 whereas processing batch sizes averaging round 100,000 prospects inside an affordable runtime of roughly 50 minutes.

Dialog Axiata has meticulously chosen occasion sorts to strike a stability between optimum useful resource utilization and cost-effectiveness. Nonetheless, ought to the necessity come up for sooner pipeline runtime, bigger occasion sorts could be advisable. This flexibility permits Dialog Axiata to regulate the pipeline’s efficiency primarily based on particular necessities, whereas contemplating the trade-off between pace and price issues.

After the predictions are generated individually utilizing each the bottom mannequin and the ensemble mannequin, Dialog Axiata takes motion to retain the purchasers recognized as potential churn dangers. The purchasers predicted to churn by the bottom mannequin, together with these completely recognized by the ensemble mannequin, are focused with customized retention campaigns. By excluding any overlapping prospects between the 2 fashions, Dialog Axiata ensures a centered and environment friendly outreach technique.

The next determine illustrates the output predictions and churn chances generated by the bottom mannequin and the ensemble mannequin.

The primary desk is the output from the bottom mannequin, which offers worthwhile insights into every buyer’s churn threat. The columns on this desk embrace a buyer identifier (Cx), a Churn Motive column that highlights potential causes for churn, resembling Day by day Utilization or ARPU Drop (Common Income Per Consumer), and a Churn Chance column that quantifies the probability of every buyer churning.

The second desk presents the output from the ensemble mannequin, a complementary strategy designed to seize extra churn dangers which will have been missed by the bottom mannequin. This desk has two columns: the shopper identifier (Cx) and a binary Churn column that signifies whether or not the shopper is predicted to churn (1) or not (0).

The arrows connecting the 2 tables visually signify the method Dialog Axiata employs to comprehensively determine prospects prone to churning.

The next determine showcases the excellent output of this evaluation, the place prospects are meticulously segmented, scored, and categorised in accordance with their propensity to churn or discontinue their providers. The evaluation delves into numerous components, resembling buyer profiles, utilization patterns, and behavioral knowledge, to precisely determine these at the next threat of churning. With this predictive mannequin, Dialog Axiata can pinpoint particular buyer segments that require fast consideration and tailor-made retention efforts.

With this highly effective info, Dialog Axiata develops focused retention methods and campaigns particularly designed for high-risk buyer teams. These campaigns could embrace customized provides, as proven within the following determine, incentives, or custom-made communication aimed toward addressing the distinctive wants and considerations of at-risk prospects.

These customized campaigns, tailor-made to every buyer’s wants and preferences, intention to proactively deal with their considerations and supply compelling causes for them to proceed their relationship with Dialog Axiata.


This answer makes use of the next methodologies:

  • Complete evaluation of buyer knowledge – The muse of the answer’s success lies within the complete evaluation of greater than 100 options spanning demographic, utilization, fee, community, bundle, geographic (location), quad-play, buyer expertise (CX) standing, grievance, and different associated knowledge. This meticulous strategy permits Dialog Axiata to achieve worthwhile insights into buyer conduct, enabling them to foretell potential churn occasions with outstanding accuracy.
  • Twin-model technique (base and ensemble fashions) – What units Dialog Axiata’s strategy aside is using two important fashions. The bottom mannequin, powered by CatBoost, offers a stable basis for churn prediction. The brink chance to outline churn is calculated by contemplating ROC optimization and enterprise necessities. Concurrently, the ensemble mannequin strategically combines the strengths of assorted algorithms. This mix enhances the robustness and accuracy of the predictions. The fashions are developed contemplating precision because the analysis parameter.
  • Actionable insights shared with enterprise items – The insights derived from the fashions will not be confined to the technical realm. Dialog Axiata ensures that these insights are successfully communicated and put into motion by sharing the fashions individually with the enterprise items. This collaborative strategy signifies that the group is best geared up to proactively deal with buyer churn.
  • Proactive measures with two motion sorts – Outfitted with insights from the fashions, Dialog Axiata has applied two principal motion sorts: community issue-based and non-network issue-based. Through the inference part, the churn standing and churn cause are predicted. The highest 5 options which have a excessive chance for the churn cause are chosen utilizing SHAP (SHapley Additive exPlanations). Then, the chosen options related to the churn cause are additional categorised into two classes: community issue-based and non-network issue-based. If there are options associated to community points, these customers are categorized as community issue-based customers. The resultant categorization, together with the anticipated churn standing for every person, is then transmitted for marketing campaign functions. This info is effective in scheduling focused campaigns primarily based on the recognized churn causes, enhancing the precision and effectiveness of the general marketing campaign technique.

Dialog Axiata’s AI Manufacturing unit

Dialog Axiata constructed the AI Manufacturing unit to facilitate working all AI/ML workloads on a single platform with a number of capabilities throughout numerous constructing blocks. To deal with technical features and challenges associated to steady integration and steady supply (CI/CD) and cost-efficiency, Dialog Axiata turned to the AI Manufacturing unit framework. Utilizing the facility of SageMaker because the platform, they applied separate SageMaker pipelines for mannequin coaching and inference, as proven within the following diagram.

A main benefit lies in value discount by the implementation of CI/CD pipelines. By conducting experiments inside these automated pipelines, important value financial savings might be achieved. It additionally helps preserve an experiment model monitoring system. Moreover, the mixing of AI Manufacturing unit parts contributes to a discount in time to manufacturing and general workload by decreasing repetitive duties by using reusable artifacts. The incorporation of an experiment monitoring system facilitates the monitoring of efficiency metrics, enabling a data-driven strategy to decision-making.

Moreover, the deployment of alerting techniques enhances the proactive identification of failures, permitting for fast actions to resolve points. Knowledge drift and mannequin drift are additionally monitored. This streamlined course of makes certain that any points are addressed promptly, minimizing downtime and optimizing system reliability. By growing this venture below the AI Manufacturing unit framework, Dialog Axiata may overcome the aforementioned challenges.

Moreover, the AI Manufacturing unit framework offers a sturdy safety framework to manipulate confidential person knowledge and entry permissions. It provides options to optimize AWS prices, together with lifecycle configurations, alerting techniques, and monitoring dashboards. These measures contribute to enhanced knowledge safety and cost-effectiveness, aligning with Dialog Axiata’s targets and ensuing within the environment friendly operation of AI initiatives.

Dialog Axiata’s MLOps course of

The next diagram illustrates Dialog Axiata’s MLOps course of.

The next key parts are used within the course of:

  • SageMaker because the ML Platform – Dialog Axiata makes use of SageMaker as their core ML platform to carry out function engineering, and practice and deploy fashions in manufacturing.
  • SageMaker Characteristic Retailer – Through the use of a centralized repository for ML options, SageMaker Characteristic Retailer enhances knowledge consumption and facilitates experimentation with validation knowledge. As a substitute of immediately ingesting knowledge from the info warehouse, the required options for coaching and inference steps are taken from the function retailer. With SageMaker Characteristic Retailer, Dialog Axiata may cut back the time for function creation as a result of they might reuse the identical options.
  • Amazon SageMaker Pipelines – Amazon SageMaker Pipelines is a CI/CD service for ML. These workflow automation parts helped the Dialog Axiata crew effortlessly scale their potential to construct, practice, take a look at, and deploy a number of fashions in manufacturing; iterate sooner; cut back errors resulting from handbook orchestration; and construct repeatable mechanisms.
  • Reusable parts – Using containerized environments, resembling Docker photographs, and customized modules promoted the convey your personal code strategy inside Dialog Axiata’s ML pipelines.
  • Monitoring and alerting – Monitoring instruments and alert techniques offered ongoing success by maintaining observe of the mannequin and pipeline standing.

Enterprise outcomes

The churn prediction answer applied by Dialog Axiata has yielded outstanding enterprise outcomes, exemplifying the facility of data-driven decision-making and strategic deployment of AI/ML applied sciences. Inside a comparatively brief span of 5 months, the corporate witnessed a considerable discount in month-over-month gross churn charges, a testomony to the effectiveness of the predictive mannequin and the actionable insights it offers.

This excellent achievement not solely underscores the robustness of the answer, it additionally highlights its pivotal function in fortifying Dialog Axiata’s place as a number one participant in Sri Lanka’s extremely aggressive telecommunications panorama. By proactively figuring out and addressing potential buyer churn dangers, the corporate has bolstered its dedication to delivering distinctive service and fostering long-lasting buyer relationships.


Dialog Axiata’s journey in overcoming telecom churn challenges showcases the facility of modern options and the seamless integration of AI applied sciences. Through the use of the AI Manufacturing unit framework and SageMaker, Dialog Axiata not solely addressed complicated technical challenges, but additionally achieved tangible enterprise advantages. This success story emphasizes the essential function of predictive analytics in staying forward within the aggressive telecom trade, demonstrating the transformative influence of superior AI fashions.

We recognize you for studying this publish, and hope you discovered one thing new and helpful. Please don’t hesitate to depart your suggestions within the feedback part.

Thanks Nilanka S. Weeraman, Sajani Jayathilaka, and Devinda Liyanage on your worthwhile contributions to this weblog publish.

In regards to the Authors

Senthilvel (Vel) Palraj is a Senior Options Architect at AWS with over 15 years of IT expertise. On this function, he helps prospects within the telco, and media and leisure industries throughout India and SAARC nations transition to the cloud. Earlier than becoming a member of AWS India, Vel labored as a Senior DevOps Architect with AWS ProServe North America, supporting main Fortune 500 companies in the US. He’s keen about GenAI & AIML and leverages his deep information to supply strategic steering to corporations seeking to undertake and optimize AWS providers. Outdoors of labor, Vel enjoys spending time together with his household and mountain biking on tough terrains.

Chamika Ramanayake is the Head of AI Platforms at Dialog Axiata PLC, Sri Lanka’s main telecommunications firm. He leverages his 7 years of expertise within the telecommunication trade when main his crew to design and set the inspiration to operationalize the end-to-end AI/ML system life cycle within the AWS cloud setting. He holds an MBA from PIM, College of Sri Jayawardenepura, and a B.Sc. Eng (Hons) in Electronics and Telecommunication Engineering from the College of Moratuwa.

Top Selling Multipurpose WP Theme


Top Selling Multipurpose WP Theme


Subscribe my Newsletter for new blog posts, tips & new photos. Let's stay updated!

Top Selling Multipurpose WP Theme

Leave a Comment

Top Selling Multipurpose WP Theme


Best selling

22000,00 $
16000,00 $
6500,00 $

Top rated

6500,00 $
22000,00 $
900000,00 $


Knowledge Unleashed
Knowledge Unleashed

Welcome to Ivugangingo!

At Ivugangingo, we're passionate about delivering insightful content that empowers and informs our readers across a spectrum of crucial topics. Whether you're delving into the world of insurance, navigating the complexities of cryptocurrency, or seeking wellness tips in health and fitness, we've got you covered.