Optimising ROI using Uplift(Causal Inference) based targeting

Enhance Marketing use cases such as purchase propensity prediction, customer targeting: channel preference, personalization of incentives, optimizing ROI for the marketing campaigns, etc using machine learning and deep learning algorithms.

Learning representation for users using various techniques.

Bottom-up data-based analysis to understand Customer-Item interaction for identifying the potentiality of the introduction of new product lining and/or creating new product categories/genres for increasing revenue.

Design and maintain scalable data processing, machine learning training, and inferencing pipeline for large-scale application.

Analyse customer behaviour and demography data to understand pattern in customer behaviour and visualize them accordingly

Understand and Build Large-Scale Machine Learning System for predicting Customer Purchase Behaviour

Leverage AutoML for understanding customer behaviour

Build machine learning models to predict customer churn

Build machine learning/deep learning models to forecast CLV(Customer Lifetime Value)

Understand how CLV(Customer Lifetime Value) can be leveraged to increase ROI of Business

Hypothesize how predicting customer behaviour will impact Revenue of the business

Build tools to annotate, audit and review data
Leverage Google cloud platform for annotating data with voice to text for increasing efficiency and throughput

Build tools to understand efficiency of content curators and provide visualisation for management to understand the issues faced by curators

Build weak supervised model to decrease time spent on training data annotations

Validation, rectification, and characterization of global master product catalog using various machine learning and deep learning techniques.
Build Labeled dataset for building machine learning models