Aatish - A New Profile-Based Recommendation Services for Mobile Telecom Network Subscribers

Saravanan, M.; Manoj, Panda; Smitha, G.B.; Lakshmi, V S

doi:10.1109/enic.2015.32

Cited by 1 publication

(1 citation statement)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This requires a method for combining RFM features into a single score, which is not very established in the current RFM related literature. In fact, except for ranking customers using the unique RFM score defined as (𝑅 * 100)+(𝐹 * 10)+𝑀 in [31], we have not encountered any similar consideration. However, similarity between nodes can be determined based on the Euclidean distance between their corresponding vectors, as has been frequently used in previous works [18,29].…”

Section: B Rfm-enriched Network Constructionmentioning

confidence: 99%

Scalable RFM-enriched Representation Learning for Churn Prediction

Mitrović

Singh

Baesens

et al. 2017

2017 IEEE International Conference on Data Science and Advanced Analytics (DSAA)

View full text Add to dashboard Cite

Most of the recent studies on churn prediction in telco utilize social networks built on top of the call (and/or SMS) graphs to derive informative features. However, extracting features from large graphs, especially structural features, is an intricate process both from a methodological and computational perspective. Due to the former, feature extraction in the current literature has mainly been addressed in an ad-hoc and handcrafted manner. Due to the latter, the full potential of the structural information is unexploited. In this work, we incorporate both interaction and structural information by devising two different ways of enriching original graphs with interaction information, delineated by the well-known RFM model. We circumvent the process of extensive manual feature engineering by enriching the networks and improving the scalability of the renowned node2vec approach to learn node representations. The obtained results demonstrate that our enriched network outperforms baseline RFM-based methods.

show abstract

Section: B Rfm-enriched Network Constructionmentioning

confidence: 99%