Best-fit mobile recharge pack recommendation
28 Mar 2013-pp 1-5
TL;DR: An adaptive recommendation model is discussed about which overcomes various deficiencies associated with existing solutions and recommends suitable recharge packs to subscribers based on their usage history and affordability.
Abstract: In today's competitive market, mobile service providers are very keen on improving the customer satisfaction by providing personalized services. Recommending recharge packs to the subscribers that suits their personal profile is an important such personalized service. But a solution to this problem is not that simple as it requires careful analysis of the subscribers' usage behavior and involves very large volume of data generated by the subscribers' frequent interaction with the telecom network. Also, this solution needs to ensure a fine balance between customer satisfaction and profitability of service providers. This paper discusses about an adaptive recommendation model which overcomes various deficiencies associated with existing solutions. The model recommends suitable recharge packs to subscribers based on their usage history and affordability. Further, it accommodates a configurable fairness parameter that ensures a balance between the profitability factor, conversion probability and relevance of the recommendations. Due to the sheer volume of the data involved, the model is implemented using a distributed framework. The validity of the model is evaluated on the basis of statistical properties and conversion factor.
Citations
More filters
01 Jan 2014
TL;DR: This work proposes a new approach based on the multi-armed bandit algorithms to automatically recommend rate-plans for new users in the Telco industry, showing promising results.
Abstract: Recommending best-fit rate-plans for new users is a challenge for the Telco industry. Rate-plans differ from most traditional products in the way that a user normally only have one product at any given time. This, combined with no background knowledge on new users hinders traditional recommender systems. Many Telcos today use either trivial approaches, such as picking a random plan or the most common plan in use. The work presented here shows that these methods perform poorly. We propose a new approach based on the multi-armed bandit algorithms to automatically recommend rate-plans for new users. An experiment is conducted on two different real-world datasets from two brands of a major international Telco operator showing promising results.
5 citations
Cites background from "Best-fit mobile recharge pack recom..."
..., who describe how to recommend best-fit recharges for pre-paid users [8]....
[...]
01 Nov 2019
TL;DR: Interestingly, top 10 impacting recharge products were found to be low cost and, with less validity, promising the rise in long-term revenue owing to increased daily-engagement with the customers by providing next best offers to the telecom prepaid customer.
Abstract: Telecom companies offer a variety of services and products to stay relevant in the competing market. However, with the vast bouquet of products/services, it becomes difficult for the customer to choose the best-fit product. The current research analyzed two recommendation frameworks i.e., An Adaptive Cognizance (AC) distance based algorithms (i.e. Cosine, Euclidean and Manhattan) and Bayesian Network (BN). Various experiments were carried out to evaluate the performance of AC and BN by comparing them with the existing recommendation system by the Telecom service provider (ES). Both AC and BN could uplift the revenue and conversion in the short term by more than 15%. Interestingly, top 10 impacting recharge products were found to be low cost and, with less validity, promising the rise in long-term revenue owing to increased daily-engagement with the customers by providing next best offers to the telecom prepaid customer.
Cites background from "Best-fit mobile recharge pack recom..."
...According to literature, most commonly, the relevant products for each user in recommendation system can be identified by measuring the distance between the usage vector and the product vector calculated using Euclidean distance [6]....
[...]
TL;DR: In this article , the authors compared two distinct recommendation frameworks: a single algorithm and an ensemble algorithm model, and found that the ensemble algorithm-based recommendation engine has proven to provide better recommendations in comparison to individual algorithms.
Abstract: In the realm of computer science, RSS is a set of tools and methods for making useful product recommendations to end users. To maintain footholds in competitive industry, telecoms provide a wide range of offerings. It is challenging for a client to choose the best-fit product from the huge bouquet of products available. It is possible to increase suggestion quality by using the large amounts of textual contextual data detailing item qualities which are accessible with rating data in various recommender’s domains. Users have a hard time making purchases in the telecom industry. Here, fresh strategy for improving recommendation systems in the telecommunications industry is proposed. Users may choose the recommended services which is loaded onto their devices. Using a recommendation engine is a simple way for telecoms to increase trust and customer satisfaction index. The suggested recommendation engine allows users to pick and choose services they need. The present study compared two distinct recommendation frameworks: a single algorithm and an ensemble algorithm model. Experiments were conducted to compare the efficacy of separate algorithms and ensemble algorithm. Interestingly, the ensemble algorithm-based recommendation engine has proven to provide better recommendations in comparison to individual algorithms.
References
More filters
30 Jul 2003
TL;DR: Output-sensitive algorithms for computing this decision boundary for point sets on the line and in ℝ2 are developed, which is the best possible when parameterizing with respect to n and k.
Abstract: Given a set R of red points and a set B of blue points, the nearest-neighbour decision rule classifies a new point q as red (respectively, blue) if the closest point to q in R ∪ B comes from R (respectively, B). This rule implicitly partitions space into a red set and a blue set that are separated by a red-blue decision boundary. In this paper we develop output-sensitive algorithms for computing this decision boundary for point sets on the line and in ℝ2. Both algorithms run in time O(n log k), where k is the number of points that contribute to the decision boundary. This running time is the best possible when parameterizing with respect to n and k.
76 citations
"Best-fit mobile recharge pack recom..." refers background in this paper
...If k = 1, then the object is simply assigned to the class of its nearest neighbor [6] [7]....
[...]