Timing is everything

: unleashing the power of best time for contact data product

Abstract

This paper explores the aspects of determining the Best Time to Call (BTC) strategy in the telecommunications industry, focusing on a case study of NOS SGPS. In today’s customer environment, knowing the time to reach out to customers plays a crucial role in business success. The study uses a dataset to uncover how scheduling calls strategically impact customer response rates. By utilizing advanced machine learning techniques such as Decision Trees, Gradient Boosting, Random Forest, and AdaBoost, the research provides an in-depth analysis of how customers respond to call attempts. These models were carefully utilized to analyze the data and identify key factors that influence call outcomes. The heart of the analysis revolves around comparing the BTC strategy with a randomized approach to determine the effectiveness of timing. The results highlight the advantages of using the BTC strategy in boosting customer engagement and streamlining processes. Maintaining standards was a priority throughout this study with strict adherence to data privacy regulations to uphold research integrity. This thesis not only adds to the academic discussion regarding customer engagement strategies but also provides valuable suggestions for NOS SGPS highlighting the wider impact on the telecommunications sector. To sum up, this thesis presents an examination of the principles and practices of call timing, combining knowledge with actionable advice and results.

Date of Award	8 May 2024
Original language	English
Awarding Institution	Universidade Católica Portuguesa
Supervisor	Nuno Filipe Loureiro Paiva (Supervisor)