How to Detect Fake Online Reviews using Machine Learning
Since Yelp’s early days, reviews are one of the most important factors customers have relied on to determine the quality and authenticity of a business.
Building a Product Recommendation System for E-Commerce: Part II — Model Building
This blog is a continuation of my previous work¹, in which I talked about how I gathered product reviews and information through web scraping. I will now explain more about how I built the product recommendation system.
Building a Product Recommendation System for E-Commerce: Part I — Web Scraping
Today, if we think of the most successful and widespread applications of machine learning in business, recommender systems could be one of the first examples people have in mind.
Uses of Automated Feature Engineering for Predictive Modelling
IntroductionI am an intern learning about generating predictive models. Manual feature engineering is a critical part of the model building process. With the advent of automated feature engineering by Featuretools, an open source python framework, manual processes can...
Generating Synthetic Datasets for Predictive Solutions
This blog discusses how the Faker tool can be used to synthetic data. Faker is used in creating a dataset for a customer engagement center for food delivery services. Models are created to validate how well the synthetic data performs.
ScoreFast™ Ratings Predictions Engine for television
Star Network is a major Asian media conglomerate netting upwards of 700 million viewers a month. They had weekly viewership ratings but sought insight into future ratings. This insight would help them proactively plan corrective action if a decline in ratings is predicted.