research.h

Time Commitment: 50 hours, Nov 23- Nov 30 ‘2018
Create baseline model with python:
* Graph theory with python
* Poster representation
* Search-Even Misspelled words
* Multiple movies attributes- Persona and Word Cloud
* Filter of Genre, IMDB rating, Popularity and actor
* Comments and Screenshot capability- Login
* Hosting with a Virtual Machine

Helpful materials:
Hosting on Shiny:
https://daroczig.shinyapps.io/rinfinance_Berlinger-Daroczi-demo/
https://www.kaggle.com/philippsp/book-recommender-collaborative-filtering-shiny
https://medium.com/neo4j/running-neo4j-on-google-cloud-6592c1b4e4e5
https://rpubs.com/jeknov/movieRec

Hosting on Neo4j: 
https://www.analyticsvidhya.com/blog/2018/04/introduction-to-graph-theory-network-analysis-python-codes/
https://medium.com/elements/diving-into-graphql-and-neo4j-with-python-244ec39ddd94
https://www.youtube.com/watch?v=c9z_ICD44XQ
https://vasturiano.github.io/3d-force-graph/example/large-graph/
https://www.analyticsvidhya.com/blog/2018/06/comprehensive-guide-recommendation-engine-python/


https://larrydag.shinyapps.io/boardgame_reco/- Very Nice, Implement this with separate reccos and final
https://www.youtube.com/watch?v=bdQ90y9Pefo&_ga=2.127414349.1156660759.1542907416-1912202818.1538049138- R+Neo4J- Exactly what I have been looking for
https://neo4j.com/sandbox-v2/- Very nice+ Shiny(Finish by 5:00 pm)
https://muffynomster.wordpress.com/2015/06/07/building-a-movie-recommendation-engine-with-r/

On selecting 10 movies, give the characteristic of persona:
Current process: Cosine similarity of movies, Pre-Train for Individual movies, 2 platforms- Tableau and Neo4j
Next Steps:
* Find method for on the fly calculations for selected items
* Get hold of More movies from IMDB(Current-Only 1700 for Hindi)
* Poster for more movies and interface for reccos with storyline and IMDB link