Netflix was the industry heavyweight. Late 2006, they released the iconic Netfliz Prize dataset. Which we will use for our analysis. This is what the raw data looked like:
|
|
|
Date: October 30, 2022
Netflix Prize Data
Our Finished Dataset
After all out data manipulating is done:
- murating = the movies average rating. From the Greek mu.
- ratingnum is the number of ratings the film received.
| movieID | title | date | murating | ratingnum |
|---|---|---|---|---|
| 3 | Character | 1997 | 3.677419 | 31 |
| 8 | What the #$*! Do We Know!? | 2004 | 3.100529 | 189 |
| 16 | Screamers | 1996 | 3.258065 | 31 |
| 18 | Immortal Beloved | 1994 | 3.750000 | 168 |
Top 10 Movies by Most Viewed
The median movie received 113 views.
A review = a view.
Top 10 Best Average Reviewed Movies
The median movie review was 3.5 out of 5.
Lord of the Rings was close, but no movie was on both lists.
More Reviews mean Higher Rating?
It appears they do. Number of reviews and average rating have a gentle Pearson Coefficient of 0.26.
Where Do Our Movies Fit?
Lord of the rings is the big winner here. With all three movies average rating above 4.4 and view count above 2000.
Did We Miss Any?
Did any other movies score an average higher rating than 4.2 and get 2000 or more reviews? Yep. There were five.
Movies that Won the Rental DVD War
| movieID | title | date | murating | ratingnum |
|---|---|---|---|---|
| 2452 | Lord of the Rings: The Fellowship of the Ring | 2001 | 4.435045 | 2317 |
| 2782 | Braveheart | 1995 | 4.273689 | 2079 |
| 2862 | The Silence of the Lambs | 1991 | 4.303144 | 2131 |
| 4306 | The Sixth Sense | 1999 | 4.302817 | 2272 |
| 11283 | Forrest Gump | 1994 | 4.272509 | 2499 |
| 11521 | Lord of the Rings: The Two Towers | 2002 | 4.475265 | 2264 |
| 14240 | Lord of the Rings: The Return of the King | 2003 | 4.549275 | 2070 |
| 14691 | The Matrix | 1999 | 4.271811 | 2281 |
| 16377 | The Green Mile | 1999 | 4.296992 | 2128 |
| 17157 | Saving Private Ryan | 1998 | 4.264822 | 2024 |