Internet Spy?

The science of all your searches.

Everyday we browse the Internet, it has become embedded in every aspect of our day-to-day lives. We use it for communication, education, entertainment, and now during this pandemic many of us depend on it to do shopping since it is best for us just to stay at home. It has been so convenient for us to get and cater the things we need in just a few taps or clicks in our smartphones or computer. But, was there a time you realize that it became overboard and it seems that most of the thing you see in the internet were pretty tailored for you or it looks like it knows you well? You might noticed it from the Ads, or maybe from suggested items/contents it offers you. Could there be an internet spy? Well that sounds creepy 🤔

Just looking at my Netflix recommendations:

Well I do like Horror, Suspense, Fantasy, Sci-Fi films and with these recommended contents for me, I would be easy for me to click and watch them.

Also, I have also observed this in my shopping app. The last time I was searching for bags and gadgets, and quite odd that it offers me the same thing right now and also shows me items that are on sale.

It amazes me that I find it personalized and makes it easier for me to find that things I need. Some will wonder and be creeped out on how are these being recorded, but really there is nothing to be scared of as this is purely technology or simply called the Recommender Systems.

Digging with our research according to Netflix, Recommendation algorithms are at the core of the Netflix product. They provide members with personalized suggestions to reduce the amount of time and frustration to find something great content to watch. They go beyond validating ideas on historical data of the viewers to understand how they actually respond to changes in their recommendation system by running online A/B tests and measuring long-term satisfaction metrics. Same goes with e-commerce sites, they have been using Recommender systems for their consumer to easily find the things they want and need which can benefit the company overall in increasing their sales.

Building a Recommender System needs to utilize algorithms we can learn from Data Science. The main purpose of a recommender system is to suggest relevant items to users. It is one of the most popular algorithms of machine learning in data science today, it has a capability in various sectors ranging from entertainment to e-commerce. Recommender Systems have proven to be instrumental in pushing up company revenues and customer satisfaction with their implementation. Therefore, it is essential for machine learning enthusiasts to get a grasp on it and get familiar with related concepts.

Recommender systems are generally divided into two main categories:

  1. Collaborative filtering
  2. Content-based systems
  1. Collaborative filtering is a technique that can filter out items that a user might like on the basis of reactions by similar users. It works by searching a large group of people and finding a smaller set of users with tastes similar to a particular user. It looks at the items they like and combines them to create a ranked list of suggestions.
  2. A Content based recommendation system tries to recommend items to users based on their profile. The user’s profile revolves around that user’s preferences and tastes. It is shaped based on user ratings, including the number of times that user has clicked on different items or perhaps even liked those items.

These algorithms can be done by doing Machine Learning for recommender systems in Python and just by using the Pandas Library we can already build a simple recommendation algorithm.

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store