Abstract: Recommender systems have become increasingly popular in recent years and are utilized in various areas, including movies, music, news, books, research articles, social tags, and products in general. Most of the existing e-commerce recommender systems have been designed to recommend the right products to users based on the history of previous users' transaction records. Thus, the recommendation system for marketing analytics is a subclass of information filtering system that seeks the similarities between users and items with different combinations.
This work focuses on content-based scoring, which aims to quantify the impact of content quality of promotional emails sent across to healthcare practitioners upon the immediate engagement.
An enhanced version of OCR is being used to extract the content from the digital media (i.e., scanned email images). The process has strived to detect the context and the localization of text information from the email and project it into a higher dimensional space with diffused information. At the same time, the pictorial features have been extracted via Morphological transformations and the HLS threshold algorithm. A semi-supervised K-Nearest Neighbor technique was implemented to extrapolate the distribution of the emails with known impact onto the ones with unknown engagement metrics due to the scarcity of performance data mapping being a significant challenge; this type of scoring system can help the business to provide more appropriate documents to suit a user's personal information need. The simulation results showed that our model could score relevant documents sent to users with higher precision than other non-hybrid information filtering models.
This approach can be extrapolated to various industries trying to optimize their marketing strategy for the digital end users. It will enable the process of getting instantaneous unbiased rating and will act as a guide to the content development team to create and publish relevant, impactful and decision-driven content. It can be used to personalize and aid precision digital marketing on the content while keeping the turn around time to minimum.
Bio: Soutir Chakraborty has joined Novartis’s Hyderabad office in August 2016 as an Analyst and got promoted to Senior Analyst in September 2018 and Manager in 2020. He is an experienced professional offering 5 years of in Deep Learning, NLP, Marketing Mixed Models, Optimization Scenario runs, Predictive Analytics, Test Control Design and Campaign Evaluation Methodology. Soutir is currently providing his expertise on Deep Learning and NLP. In past, he managed the entire process Marketing Mix Model and Optimization Scenarios for US GenMeds. He also played a pivotal role in Digital Medicines while working on Test Control Designs and Campaign Evaluation Methodology. Soutir holds a Masters degree from Indian Statistical Institute, Kolkata . Soutir holds a Bachelors degree from West Bengal University of Technology, West Bengal.
Manager | Novartis