Our current focus at HelloMovies is to achieve such simplicity without sacrificing functionality. We have lots of information on films, many different ways for users to share their opinions on films, and many thoughts on how to use all of this data to enable the discovery of new movies. Unfortunately, packaging everything into a Website that services both the casual user who wants to find a movie to watch and the power user who wants to rate and catalog 1,000 movies will not be easy.

Thankfully, we are starting to meet some talented and experienced friends to guide us in the direction of such polished and easy-to-use Websites as Shelfari and Mint.

We also added a few more pages including a Genome Requests page and a Top Rated Movies page. The Genome Requests page lists movies that need additional tags and the Top Rated Movies page includes such lists as:

Guilty Pleasures (movies people like, but aren’t very good)

1. Any Given Sunday
2. The Thomas Crown Affair
3. Serendipity
4. Legally Blonde
5. Closer

Worst Movies

1. Daredevil
2. Scary Movie
3. Honey
4. Hostel
5. Balls of Fury

Finally, we’ve made some layout changes to each of the movie landing pages to make it easier for people to rate, review, and tag movies. If you’re registered on the site, let us know what you think of the recent updates!

We also have a new top movie watcher on the site who has watched 855 movies and counting!  Tammie, you definitely deserve some more recognition on our site. I’ve personally found a lot of new movies to watch based on the movies you’ve rated and the genes you’ve contributed. Thank you!

The site and the team have both come a long way in that time. Although I know there is still a lot to do, it’s pretty cool to look back on our footsteps and see how far we’ve progressed since we first came together in a Mirrielees dorm room. I miss version 1.0…

Stan is a Movie.

Orange! Hello Halloween.

A Keanu Whoa.

The site is now going through some major updates including improvements to Search, the Movie Genome Project, and community tools for cataloging and rating movies. We also have yet to showcase our primary reason for developing the Genome, providing great movie recommendations. Given all of Hamilton’s prior posts, it’s safe to say that this is coming along with a lot of attention and thought.

Thanks to all those who have signed up and taken time to check out our site! We look forward to your Feedback.

Say my lists are a and b.  I’m concerned with the most computationally intensive part of the function, the calculation of the symmetric difference.  Here’s one approach:

[elem for elem in a if elem not in b] + [elem for elem in b if elem not in a]

But this ends up taking anywhere from .8 to 1.4 seconds for the 60,000 function calls.  Too long!  I thought perhaps if I can collapse it all into one list comprehension, then I’d be fine … maybe the issue is the fixed cost of calling the function:

[elem for elem in set(a+b) if (elem in a and elem not in b) or (elem in b and elem not in a)]

But this is even sillier - not to mention it takes a ton of time.  Anywhere from 1 - 1.8 seconds for the calls.  So why not just use python’s set type?  I can then turn my code into this guy:

a, b = set(a), set(b)

sym_diff = a.symmetric_difference(b)

This takes about .2 - .4 seconds, which is a great improvement, especially considering the number of calculations I’m making.

Moral of the story: list comprehensions are pretty handy, but not particularly efficient.  I’ll report more after I jump into the C code that dictates these operations.  Likely I could cut down this run time even more!

“Son of Rambow,” a coming-of-age comedy about two boys in England who dream of filmmaking, was a darling at Sundance in 2007, where it was reportedly sold for distribution for about $7.5 million - one of the largest buys at the festival that year.

Vantage released the film in May 2008 to top-notch reviews.  But it flopped, grossing just $1.78 million.

…

” ‘Son of Rambow’ is the poster child for a movie that would have worked five years ago but fails in today’s marketplace,” says Mark Gill, a veteran film executive who isn’t affiliated with the movie.  “It got great reviews, audiences really liked it, it was well-marketed.  It had everything going for it, and yet it didn’t work, because tehre is such a glut for movies and a mass of clutter right now that nothing can break out in this climate.”

This is a shame for the industry, but it means something important - Hollywood is generating number of movies that we’d call “hidden gems” - really great movies that failed at the box office for various reasons.  One of our big goals is to make sure that users will be able to mine for the plethora of great hidden gems out there.

Or does it depend on the individual user?

It’s tough.  Movies are so darned multifaceted, that making comparisons between them is quite the task.  Competitors for the Netflix Prize have utilized users to determine what movies are similar; if person A and person B like movie C, and person A also likes movie D, then perhaps person B might like it, too.  Those movies are sufficiently ’similar’ to each other, based off of inferred preference.  Now, a great deal of sophistication has emerged from that simple model, taking other movie features into account.  We like to think that we’ve got a wealth of data to make some well-informed comparisons between movies.  And not just on a few of a movie’s overall features - on ANY feature worth noting.  So, if you like this movie’s cinematography, we’ve got a list of movies that you might enjoy.  Or story.  Or actors.  Or character types.  Or budget.  Or, …

Just food for thought.  Perhaps a brief sneak peak at what’s to come.

1. Donnie Darko
2. The Rocky Horror Picture Show
3. Snakes on a Plane
4. Napoleon Dynamite
5. Repo Man
   
6. Army of Darkness
   
7. Eraserhead
   
8. House of a 1000 Corpses
   
9. Fight Club
   
10. Carnival of Souls (the 1962 version)

I personally had never heard of Carnival of Souls, but its definitely on my “To Watch” list now.   At any rate, I’m not going to ruin the plethora of surprises, but similar awesomeness abounds with other genres.  Screwball comedies, slasher flicks, dark french comedies from the late 70’s with Gerard Depardieu (gold star to the fella who knows what movie(s) I’m talking about) and this and that and this and that …

For all my excitement about the future of recommendation services, I can’t help feeling the way I felt about search in 2001. Existing recommendation engines have a lot of value, but they’re still primitive. Distinctions between browsing and comparison (that is, between looking at products and choosing between them) are poorly understood. We’ve yet to see how user-generated tags make product and service descriptions more precise and useful. The more specific, explicit, and time-sensitive the tag, the better the potential recommendations will be.

Smart people all over the world are working on these problems. Billions of dollars are at stake. Netflix is offering a million dollars to anyone who can improve the efficacy of its (exceptionally successful) recommendation engine. That’s a small price to pay for a company whose future depends on its ability to compete with Blockbuster and the digital video delivery companies of the future. It is an interesting and important problem, because it’s not only individuals who watch the movies, but couples, families, and friends. Perhaps the winning algorithm will be optimized for the preferences of groups.

When I get good recommendations, I spend my time and money differently. Even better recommendations will dramatically increase the value of that time and money. That’s a digital future I crave and expect. I hope Internet innovators take my recommendations as seriously as I take theirs.

Not that we need the validation. The point is I fully agree that better recommendations are needed especially as we are increasingly overwhelmed by mounds of content.