Hacker News new | ask | show | jobs
Movie recommendations based on your personal taste (taste.io)
138 points by lifwanian 3622 days ago
42 comments

Nice work !

But :

"About us" (http://www.taste.io/about): There is nothing about you...

You ask people for their names, email addresses and/or to link to their facebook accounts but you don't return the courtesy of identifying yourself or your company.

You make some promises and cite some laws about privacy (http://www.taste.io/privacy-policy) but if you don't say who you are, we can't even be sure that those apply to you...

These guys are trying hard to hide their identity. No business name or address. No SSL cert. Anonymously registered domain in Panama. Hosted by a telecom in Sweden. Nothing in Google, Facebook, or LinkedIn.

The "Privacy" page gives a hint. It gives a contact address of "contact@ymal.io". "ymal.io" just redirects back to "taste.io". But WHOIS gives some info for "ymal.io". It's registered to [redacted].

That location is a 5-story building, but the most likely location is Spark Labs, which is a co-working space.[1] $550 a month for a desk. And, yes, "ymal.io" is listed as a member of Spark Labs.[2] So, if you need to find them, that's where to look.

[1] http://www.desksurfing.net/desks/1045-spark-labs [2] http://spark-labs.co/members/

We redacted the name and street address. Even if it's publicly available info, posting it here crosses a line that in general it's a bad idea for HN to cross.
This is a passion project and we have day jobs. Write to us on Facebook or email, we're very good at responding and making improvements accordingly. Thanks for the support!
Some of us have to hide identities as it can affect our current employment.
From a user's perspective it looks shady and shouldn't be the basis one starts a business on.
not so hard to find using OP's nickname on twitter...

If they are really hosted in Sweden, does the collected data is under Swedish law and not US as mentioned on privacy page ?

Not only that but the Privacy Policy is a straight up lie. No https yet:

"In addition, all sensitive/credit information you supply is encrypted via Secure Socket Layer (SSL) technology.

We implement a variety of security measures when a user enters, submits, or accesses their information to maintain the safety of your personal information."

I really like the service, but it's free to get https setup and takes just about 0 effort thanks to letsencrypt.

Yep, login with POST to http://www.taste.io/auth/local and creating an account (POST http://www.taste.io/api/users) are made without ssl. name, password and emails are sent in clear over the network.
If you want a better recommender, check out tastemonster.com :)
I love the fact that the ratings are semantic, and limited to four easy to understand values rather than 5 stars:

    Awful (Can I have those two hours back?)

    Meh (Not great, but better than nothing 
         to kill time, escape or veg out)

    Good (I enjoyed watching it)

    Amazing (I'd watch it again and recommend
             it to friends without hesitation)
With 5 stars, everyone interprets 2, 3 and 4 stars differently, e.g.:

    Horrible  Bad  Meh   Good       Best

    Bad       Meh  Good  Very-Good  Faves
Even the same person over time will not use a 5-star scale consistently. Even when I try to be consistent (I use the latter values for Netflix), if I like a movie but don't love it I don't know whether to give it 3 or 4 stars. On different days in different moods I'll make different choices.

I've no doubt that unreliable ranking data made Netflix recommendations harder, and impacted their mix of recommendation algorithms -- i.e. leaning more heavily on those that work despite rating scale inconsistencies. I'd expect the mix that works best for Taste.io will be different.

I have to agree that the rating options are very refreshing and easier to keep consistency over time. It also forces a choice between positive and negative which I'd imagine helps the algorithm learn things faster. Hmm...
I'm impressed. It gave me what I thought to be a small, weak data set, but the recommendations were better than those I get from Netflix, which has much, much more of my data to work with.
> the recommendations were better than those I get from Netflix

I can tell you exactly why Netflix makes such poor recommendations, and why almost anyone can do better with modest effort:

Netflix has to give recommendations for you from the 6000 movies that it's currently showing[1]. They can't recommend movies that they don't have. Whereas Taste.io can choose from the entire universe of ~500,000 movies.

An example should make this clear: If you liked The Godfather, it's an easy prediction that you'll like The Godfather: Part II and Part III. Suppose Netflix is currently showing The Godfather, but not the sequels. They cannot recommend the sequels to you. But Taste.io is not bound by that restriction; they can in theory recommend any movie that exists. It's much easier to find matches among 500,000 movies than among 6000.

[1] Netflix has just 6332 movies in the USA as of this date and even less in other countries (eg., 4365 in Canada). Most people are surprised by how few movies Netflix actually has. The Netflix user interface makes it very difficult to get a good impression of the number of movies; you can't just scroll alphabetically through the entire list for example. Source: http://netflixcanadavsusa.blogspot.ca/

Presumably Netflix are using a wider system to choose which movies to licence? I wonder what their process for adding movies is - do they have a list from each studio they work with and select a movie to add, out do the negotiated each one separately.

Seems they could have a not yet available category that would let people pre-order; they could recommend a far wider swathe of content then.

It's been reported they use piracy sites to gauge popularity. They probably have other deciders too, this one's the most interesting though.

https://torrentfreak.com/netflix-uses-pirate-sites-to-determ...

I get what you're saying, but Netflix seems even worse than that. To wit: taste.io recommended movies for me - which I enjoy and that are in Netflix's current catalog - that Netflix hasn't recommended for me.
> An example should make this clear: If you liked The Godfather, it's an easy prediction that you'll like The Godfather: Part II and Part III.

Really? I've always heard such negative things about Part III that I never bothered to watch it.

Also why the Netflix reccomendation system used to be a bigger selling point for them before they switched to streaming.
What makes the rankings better than you get from Netflix? I'm impressed that it managed to suggest Clue to me, but I haven't seen the rest, so can't really say if I would like them. (More, if it just suggests movies I've already seen and liked... hard to say it did a good job, or that I'm just predictable in cliques of movies. :) )
The point of this site is to give you recommendations you haven't seen. I hate it when all the recommended movies on Netflix are all movies I've seen and can't get rid off...
Agreed. I just don't know how I could "rate" that the site is recommending good movies until I have watched them.

That is, I'm curious how so many folks are claiming it is doing a great job.

They all look interesting. Many years ago, netflix did the same. It recommended me a bunch of movies that seemed really interesting and I liked a ton of them, but these days netflix is a low bar. I'd bet they could do a great job, but have a more limited movie selection. Either that or the algo has actually declined.
Are you just on streaming? I've noted that the recommendations for streaming are fairly restrictive since they only have around 6000 movies available at a time.

With DVDs, the greater selection means better recommendations.

Or payolla. Never assume a bad algorithm when a good algorithm makes less money.
These recommendations are pretty crazy (in a good way). All my favorite sci-fi, comedies and thrillers in one list. Impressed. Going to check all the ones I haven't seen
Same here. It showed me a bunch of blockbusters that I either haven't seen, were just kinda good, or even meh.

And came up with amazing recommendations of really cool movies I've either watched and loved, or haven't seen but always wanted to. Even the top pick for "movies from this year" was the one movie where I saw a trailer and said WANT.

I was surprised too. I didn't really connect to any of the choices during building the profile but the recommendations were right on.
So I am tired of having to manually rate every movie for every new service. Why isn't there a way to keep all my ratings as an interchangble file? I spent about 2 hours ratings abou 1000 movies. I've done the same before for Netflix etc. seems like a huge waste of time, we need an open API for all these services.
https://trakt.tv/

Alternatively I've seen more than a few things use IMDb, or Rotten Tomatoes.

Trakt used to be excellent until they decided to redesign everything. I tried giving the new site a chance but ultimately decided to stop my VIP subscription and move on.
We'd love to hear any feedback or suggestions you have via our support site. That's perfectly fine if you've decided to move on. Just wanted to point out the site has evolved a ton since the initial v2 launch over 1.5 years ago if you're interested in giving Trakt another chance :)
I guess I could give it another go. Didn't realize it's been that long alright.
Shoot us a message at support@ if you have any feedback or questions.
I had fun playing with this, but what I noticed is that the recommendations started well, but as I rated more movies, they became less and less accurate.

Is it possible that whatever technique you are using to model individual users is overfitting to noise in their ratings?

Wow this great! Beautifully designed and delighted to see someone using 4 options rather than 5 it's so much easier.

Profile is at 90% and have only heard of 3 in all my top matches, very interesting. Ugestu from 1953 is the top at 100%, what exactly does the 100% mean? Excited to watch it now!

Is this supposed to be a Show HN?

Where does it get your move list from? I know I rated a lot of movies on my rotten-tomatoes profile, can this be used?

EDIT: Also, it's not clear that you can start using the product without Facebook, I like the fact that it lets you rate a couple movies before asking you to sign-up (with Facebook or with a regular email/password)

Facebook auth is also failing for me as I receive an internal server error during auth.
Hey! I work on the site, sorry for the mishap. You should be able to authenticate now!
I just spent a good hour adding every movie I can remember seeing. The suggestions still look like ORDER BY RAND() of every movie made since the 60s.

What a waste of time, again. I had a similar experience on tanktop.tv a year or two ago, though that did a slightly better job of at least suggesting modern (well-made) movies.

Is there any way to filter the recommendations down to the offerings from various content providers?

E.g. 'Available streaming on Netflix'

Coming soon!
I've rated many films on Netflix. It would be cool to be able to import my ratings from Netflix (or similar services like Amazon Video or IMDb) into Taste.io. Your service would get a lot more data to work with. :)

So far the recommendations have been very good and I've bookmarked a couple films to watch later.

Awesome, thanks for this.
Very interesting. This did two things:

1. Correctly identified a bunch of movies I had seen and really liked + some promising ones I hadn't seen, and 2. Showed me that I don't like any new movies

None of the 2016 movies were over 70% for me, whereas it identified some movies I had seen and loved as 97+%.

How does this work?

I had a similar experience. Every highly rated recommendation was either one of my favorite movies or on my list of movies I need to see very soon but haven't made the time for yet.

It knew to put The Holy Mountain at 100% based off me loving the new Mad Max, feeling ambivalent about the Star Wars prequels, hating the 2007 Tranformers movie, and thinking Anchor Man was good but not great. Like, how the hell? It's spot on, but how did it get that from my input? Is there more info on how this thing is getting its results? I would love to see even a sketchy outline of the algorithm.

Would be awesome to have import option from CSV file. After jinni.com folded, I've been tracking my movie ratings in spreadsheet file.
Nice, the rating consensus system makes me curious about some stats, like for all users, the best movies with high consensus, and a list of good movies with least consensus.
Interesting question, just ran a quick analysis for all movies rated 4.5+ star

Highest Consensus:

1. Whiplash

2. 12 Angry Men

3. Se7en

Most Controversial:

1. Birdman

2. Citizen Kane

3. 2001: A Space Odyssey

There must be problem with your dataset then. Not enough people? Everyone in this field knows that Napoleon Dynamite is the most controversial, ever.
> 1. Birdman

I knew that abomination was polarizing, but i did not quite expect that.

Abomination? That was oone of my favorite movies of all time!
;)

It's an emotion vs intellect thing. Birdman is like cocaine to people who like the emotional side, and like hydrochloric acid for people who want a movie to be rational.

I'm just surprise the numbers even bear that out like that.

><
Can you please show release dates? Sometimes I'm not sure if a movie is the original or a remake.

EDIT: The release date is included in the URL for the movie.

Very impressive.

Recommendation are excellent - I noticed that recommendations are NOT about movie genre but about how the movies are made, their point, story, etc.

I.e., I hate when Netflix thinks that I like all stupid vampire movies because I liked Thirst [1].

[1] http://www.imdb.com/title/tt0762073/

One thing I've noticed is that it's not very good with sequels.

For example, I liked the original Planet of the Apes, but I've absolutely hated every single one since. Yet it keeps recommending more sequels even though I've marked them "awful".

I've also noticed that it won't stop recommending various Lord of the Rings movies, even though I've marked every single one of them as awful.

I'm still not sure if the recommendations are good or not. I'm at 92% now, and half the recommendations it gives that I've already seen are bad, so I'm not inclined to believe the ones I haven't seen yet.

I also noticed that it started out with lots of sci-fi and action movies, to the point that I had to start manually searching for romance movies just to get them to even show up. Basically, after the first 4-5 movies, you're stuck in a genre.

I am curious why you used the user-closeness model.

Matrix factorisation won the Netflix prize: http://dl.acm.org/citation.cfm?id=1608614 . What made you go for user closeness?

We've tested other models but collaborative filtering gave us the most "human"/natural results. Also, didn't Netflix toss the matrix factorization after the contest? IIRC they decided to keep their current algorithm.
Interestingly, my sense has been that Netflix's recommendation engine does a poorer job now than it did 10 years ago. I always assumed that it was because they used to use fairly straightforward collaborative filtering, and now they seem to be heavily focused on looking for stuff that's somehow cosmetically similar to other stuff I've watched.

So, like, instead of saying, "You liked Nosferatu? Well, other people who liked Nosferatu also liked Ran, so let's suggest that," it now goes, "Hey, that's a vampire movie! How about Blade?"

Nice! I'd love to be able to point it to my IMDB data. Both because it's got a comprehensive list of my ratings, but also so that it knows which movies I've seen to avoid recommending them!
Did this work for anyone? Meaning; anyone got good (for them) suggestions? Where does the data set come from?

Am I blind or did I miss the button for 'I did not see this movie'? Because I didn't see quite a lot of the ones that I was asked my opinion on.

All in all, I always like these kind of things, but asking me if I like that Star Wars drivel 3 times in a row and then asking me if I liked 4 movies I never saw skewed my results a bit I think.

Keep improving though! If I can get only one 'wow' movie I never saw recommended, I would be really happy.

There's a "Haven't Seen" button right below the 4 circles. (At least for me :/)
A there is not for me (Chrome on Linux). I found it by trying some zooming options. Thanks.
Suggestion of 'Spirited Away' based purely on my ratings of X-Men and Saw? Spot on! I would love to read about the algorithm you guys are using (in an upcoming paper perhaps? :))
Indeed! I'm baffled. Is there a dataset of film style this is drawing on, or is it purely based on prior user trends?
What I've always hoped for from a service like this is explicit sequel recommendation.

Of course, you might get it organically since the original film and its sequel are presumably pretty similar, but it would be nice to have some kind of list of unseen sequels for those films which you gave a positive rating.

Maybe my fingers are to fat. Everytime I tried to Click/Touch the skip Option, it rated a movie good...
It would be great to have my ratings in a public profile. After getting to 94% I can send it to friends so they can check out if they've seen all movies I consider amazing and good.

By the way, Friday evening is a bad day for a "ShowHN" post.

I already maintain a list of movies to watch based on whatever interests me on netflix + random lists on internet. I took their quiz and their recommendations had good overlap with my existing list. Impressive!
This site begs for a IMDB rating import function... I've rated hundreds on movies on there, but I'm not prepared to do it all again on a different site while all the data is already for the grabs..!
BTW, loving the idea and already found some promising new movies to watch!
I don't think I got good recommendations (based on the ones I've seen) but then again I have peculiar tastes; I think Lilo and Stich is a great movie and se7en is a meh movie (and I can argue why).
>and se7en is a meh movie (and I can argue why).

I challenge you.

well, I've seen it twice and it's a fine movie but I don't see there's anything special about it, the serial killer using a theme has been done a million times, the only twist is the motivation/endgame of the killer in this case. Acting is good and overall the movie is entertaining but I fail to see anything other than a build-up for the grand finale (goo but not mind-blowing or totally unexpected), it's a 3.5/5 or 4/5 for me, still can't see why it consistently shows up in top movie listings.

OTOH I haven't been wowed by a movie since The Matrix so I'm probably just an old man yelling at the clouds.

Cool user flow. I bet you could hit me with another facebook login request with the "see your results" popup, and I might not even mind it. That said, I won't click it.
Appears I reached the end of all the movies. Says theres only 1715 movies. Either thats incorrect or there's a very tiny amount of movies imported.
Playing around with it I'm finding the interface notably more friendly than MovieLens.org for inputting ratings, but the results seem worse.
Very cool. My list of recommendations included movies I greatly liked, as well as ones that have for a long time been on my to-watch list.
Are others getting a lot of recommendations for old movies? I have to be in just the right mood for a movie from the 1950s or earlier...
You can use the filter on the browse page to filter out old movies, or simply hide them!
This is good. Impressive. It managed to recommend me Soyaris, a Russian film based on the same book Solaris was based on. Great film.
It would be cool if you could use this to find people with similar taste, i.e. mentally and geographically proximate.
For me this was significantly worse than Netflix and others I've tried. Looks like others have fared better.
Some pretty nice recommendations! I got Barton Fink, Throne of Blood...movies I'd never think about otherwise
I've love to see this integrated with a TV/Movie scrobbler such as trakt.tv.
That suggested some obscure movies that I like, wow!
Nice work. ps - millennium has two Ns in it
what database (movies API) are you hitting ?
Currently using iTunes but will be moving to TMDB soon
Very impressive!
My impressions in order from positive to negative are that the visual appearance is great, the UI is OK, and the actual recommendations are poor.

For the UI, I think a verb like "Rate" would be much better than "I've seen this". I like the in-place popup with the stars. Unlike some others, I felt like having 4 options didn't let me distinguish between movies that were enjoyable, and movies that I'd call my favorites.

Showing a movie summary on hover would be helpful. Clicking the image and then going back scrolls to the top of the page if you rated the movie on the details page. Inability to click to see details on movies already rated was awkward, as sometimes I'd rate a movie and then be unsure if it was the movie I thought it was. Would be nice to know if "Hide" implies "Not Interested" for the recommendations, or just doesn't show it again.

I liked the ability to just jump in and rate things, but forced sign up to proceed felt slimy. Better to nag here ("Your ratings might be lost if you leave the site before you create an account") than sneak up on the user and force them to comply. If it hadn't been a Show HN, I would have bailed here.

The real problem for me was the quality of recommendations. I rated 300+ movies, and didn't feel like I got any recommendations for movies that I felt at all compelled to act on. I don't think any of the recommendations were ones that I'd rate as "Amazing", and I didn't see any drop off in "likability" from the top to middle of the list. Obviously some of this is preconception (maybe I'd love that particular Disney film despite disliking all the others) but preconception needs to be considered to build the user's trust.

The recommended movies that I knew about were generally in the "classic that everyone likes but I don't care about" class. It felt like many of the movies that I didn't know about were mostly in the "popular sequel to a movie I've already ranked as awful". If I've already ranked multiple Batman and Superman movies as awful, suggesting that I have a 63% match the "Batman vs Superman: Dawn of Justice" makes it hard to trust your methods.

Much of the problems for me are probably caused by the small dataset you are using, not just in terms of ratings but in the catalog itself. I was able to find some of my favorite movies by searching directly for them (Primer, Adam's Apples, Once Were Warriors), but many just weren't in your dataset (Ararat, Metropolitan, Fast Cheap and out of Control, Incident at Loch Ness). Bootstrapping a recommendation engine is difficult, but for me I didn't feel I got any return on effort.

The things that would most improve the site for me would be browsing with item-by-item similarity (people who loved this also loved), ability to directly see ratings by people with similar tastes (needs to be opt-in), ability to see "sandbox" recommendations (if I liked X and hated Y, and if my wife like Y but hated Z, what movie would be both enjoy?), ability to browse by director (I presume others would want actor), and ability to filter recommendations by date (in my case, exclude any pre-1980 films).

Good luck!

Has this been around for a while, and gotten a recent facelift? I remember something very similar (and may have even been called Taste) back in 2013.
The site is only a few months old, if you could remember the other site I'd love to know.
I was looking for something a few months ago, and a friend recommended this site he'd been using for many years: http://www.filmtipset.se/
Suggestions:

* -Awful-Meh-Okay-Good-Great-Amazing-

*Show the year next to the title of the movie when in browsing view.