Skip to content

Latest commit

 

History

History
45 lines (25 loc) · 2.43 KB

SecondCapstoneIdeas.md

File metadata and controls

45 lines (25 loc) · 2.43 KB

3 Ideas for Second Capstone Project

Idea 1 - Quick, Draw! Doodle Recognition Challenge

Background

Quick Draw app was release by Google to educate public in a playful way about how AI works. The game prompts the user to draw an image depicting a certain category like an airplane, bug etc.

Dataset

The Quick Draw Dataset is a collection of millions of drawings across 300+ categories, contributed by players of Quick, Draw! The drawings were captured as timestamped vectors, tagged with metadata including what the player was asked to draw (label) and in which country the player was located.

Problem

The goal is to develop a pattern recognition classifier that can classify a new hand drawn image into one of the given 300+ categories.

Idea 2 - Google Analytics Customer Revenue Prediction

Background

As with all businesses, Google merchandise store wants to invest appropriately in the promotional strategies and wants to target most revenue producing customers.

Dataset

The train data set contains 900K rows. Multiple columns contain JSON blobs of varying depth. Some of the columns are date (when customer visited the store), session information (customer's session), device (used to access the store) and totals (json having transactionRevenue that is to be predicted).

Problem

Goal is to predict revenue per customer for the online GStore.

Idea 3 - Movie recommendation

Background

Recommendation is the need of today. Not only businesses want to recommend next item to their customers. But customer too wants to know what items he might like next. As a customer it helps to wade through the ocean of choices.

Dataset

These files contain metadata for all 45,000 movies listed in the Full MovieLens Dataset. The dataset consists of movies released on or before July 2017. Data points include cast, crew, plot keywords, budget, revenue, posters, release dates, languages, production companies, countries, TMDB vote counts and vote averages. This dataset also has files containing 26 million ratings from 270,000 users for all 45,000 movies. Ratings are on a scale of 1-5 and have been obtained from the official GroupLens website.

Problem

Building Content Based and Collaborative Filtering Based Recommendation Engines.