[{"data":1,"prerenderedAt":344},["ShallowReactive",2],{"project-23541840":3},{"id":4,"name":5,"line":6,"line_source":7,"title":8,"url":9,"domain":10,"maker":11,"posted_at":12,"year":13,"points":14,"comments":15,"rank_in_year":16,"shown_in_year":17,"top":18,"tier":19,"category":20,"subcategory":21,"format":22,"keywords":23,"reception":27,"sentiment":28,"stance_mix":29,"scored_comments":34,"aspects":35,"strip":41,"post_text":43,"what":44,"said":76,"maker_in_thread":177,"shape":187,"grid":192,"attempts":295,"same_week":306,"maker_shows":254,"maker_hidden":336,"reader_version":337,"card":338},"23541840","Findka","Personalized recommendations for any type of content","title","Show HN: Findka – Personalized recommendations for any type of content","https:\u002F\u002Ffindka.com","findka.com","jacobobryant",1592329259,2020,96,45,671,3028,23,"notable","ai","recommender system","web_app",[21,24,25,26],"collaborative filtering","content recommendations","music recommendations","curious",-0.024,{"positive":30,"neutral":31,"mixed":32,"critical":33},4,13,1,3,21,{"idea":36,"execution":37,"performance":39,"design":40},{"positive":32,"critical":32},{"positive":38,"critical":32},0,{"positive":38,"critical":38},{"positive":32,"critical":32},[38,42,38,32,38,33,38,38,38,33,38,33,38,33,38,32,38,33,38,42,38,33,38,32,38,38,38,38,33,38,42,33,33,38,33,38,42,33,38,33],5,null,{"problem":45,"audience":43,"pricing":43,"motivation":55,"time_to_build":43,"stack":59,"openness":74,"stage":75,"team_size":74},{"value":46,"source":47,"evidence":48},"Finding interesting content across books, music, articles and movies without a specific search query","maker",[49,52],{"id":50,"by":11,"text":51},"23541862","(Reposting, again, with permission from dang) Hi, OP here. I started working on recommender systems in 2016 during my undergrad, specifically doing music recommendation (I was…",{"id":53,"by":11,"text":54},"23542690","I've wondered about this a lot. It seems to be hit or miss--some people love e.g. Spotify's discover weekly\u002Fdaily mix playlists, and some people hate them. I suspect that some…",{"value":56,"source":47,"evidence":57},"Maker was dissatisfied with music recommendations and wanted a cross-domain recommender",[58],{"id":50,"by":11,"text":51},[60,64,68],{"value":61,"source":47,"evidence":62},"Clojure",[63],{"id":50,"by":11,"text":51},{"value":65,"source":47,"evidence":66},"DigitalOcean hosting",[67],{"id":50,"by":11,"text":51},{"value":69,"source":47,"evidence":70},"Last.fm API for music search",[71],{"id":72,"by":11,"text":73},"23561532","Thanks for the feedback. - I'll add an option for this. - What songs were you searching for? The search feature uses Last.fm for music. They've had pretty much everything I've…","unknown","launched",{"praise":77,"objections":86,"requests":116,"questions":139,"alternatives":151},[78],{"value":79,"source":80,"evidence":81},"Gnod and Gnoosic-style discovery is useful","commenter",[82],{"id":83,"by":84,"text":85},"23542923","TicklishTiger","Reminds me of Gnod, the Global Network Of Discovery: https:\u002F\u002Fwww.gnod.com For music, Gnod definitely gives me better suggestions then iTunes and Youtube.",[87,98,109],{"value":88,"source":80,"evidence":89},"Cross-domain correlation between content types may be weak",[90,94],{"id":91,"by":92,"text":93},"23542238","aabeshou","It's an interesting idea. Do you have reason to believe that people's preferences in different areas are correlated? Not saying they're definitely not, but that's my first…",{"id":95,"by":96,"text":97},"23546571","brmgb","I am going to share a piece of anedoct. There once was a very nice German-based application called Foundd. The app was soecialised in movie recommendation and it was awesome:…",{"value":99,"source":80,"evidence":100},"Cold start: new users get irrelevant items they cannot rate",[101,105],{"id":102,"by":103,"text":104},"23548618","steveharman","I love the sound of this. But wouldn't it be productive for users to initially \"seed\" a category (say, Movies) by entering a handful of films they liked and ones they didn't…",{"id":106,"by":107,"text":108},"23547611","victor9000","Biggest advise I can give is that you should do a better job at content seeding to ensure that first time users have a good experience. Otherwise, you'll never get better from…",{"value":110,"source":80,"evidence":111},"Music recommendations feel mainstream and poor",[112],{"id":113,"by":114,"text":115},"23542437","xerox13ster","> I started working on recommender systems in 2016 during my undergrad, specifically doing music recommendation (I was dissatisfied with the quality of Pandora\u002FSpotify…",[117,125,132],{"value":118,"source":80,"evidence":119},"Seed preferences with a search box for items",[120,121],{"id":102,"by":103,"text":104},{"id":122,"by":123,"text":124},"23542601","julvo","Neat idea, this could become a valuable resource for discovering interesting things. From a UI perspective: Maybe there could be a searchbox for books, songs etc. so that one can…",{"value":126,"source":80,"evidence":127},"Import ratings from Letterboxd, Goodreads and similar services",[128],{"id":129,"by":130,"text":131},"23543511","bobcostas55","This would be much better if it allowed you to import ratings from other popular rating services (letterboxd, goodreads, RYM, etc.)",{"value":133,"source":80,"evidence":134},"Option to change number of recommendations in newsletter",[135],{"id":136,"by":137,"text":138},"23561134","emaro","Very interesting. Learned about Findka in your music recommendation service newsletter. - I'd like to change how many recommendations I get with each newsletter. - I'd like to…",[140,144],{"value":141,"source":80,"evidence":142},"How correlated are preferences across content types?",[143],{"id":91,"by":92,"text":93},{"value":145,"source":80,"evidence":146},"How well does it scale in users and data?",[147],{"id":148,"by":149,"text":150},"23545551","Thespian2","You mention storing the matrix in memory and recomputing hourly because of the small data set. What are your estimates for scaling ceiling with current implementation? How many…",[152,156,162,169,173],{"value":153,"source":80,"evidence":154},"Gnod",[155],{"id":83,"by":84,"text":85},{"value":157,"source":47,"evidence":158},"Gnoosic",[159],{"id":160,"by":11,"text":161},"23542948","Definitely. Gnoosic in particular was an inspiration for the current iteration of Findka (https:\u002F\u002Fwww.gnoosic.com\u002F).",{"value":163,"source":80,"evidence":164},"Stumbleupon",[165],{"id":166,"by":167,"text":168},"23547519","devnonymous","This reminds me of Stumbleupon[1] from back in 2005-ish. I used to love using it before they decided to pivot and remove all of the things that made it great. [1]…",{"value":170,"source":80,"evidence":171},"Foundd",[172],{"id":95,"by":96,"text":97},{"value":174,"source":80,"evidence":175},"Spotify Discover Weekly",[176],{"id":53,"by":11,"text":54},{"comments":178,"answered":42,"key":179},20,[180,181,184],{"id":50,"text":51},{"id":182,"text":183},"23542519","I've thought a fair amount about inferring preferences (i.e. explicit vs. implicit feedback). Particularly for music, tracking skip data and feeding recommendations to the music…",{"id":185,"text":186},"23542446","Thanks for the heads up. Turns out the default url that google books returns often gives a 404. I fixed that last night but haven't updated all the previously imported books yet.",{"commenters":188,"max_depth":189,"maker_replies":178,"first_comment_mins":190,"lifespan_hours":191},19,6,2,319,[193,195,199,200,204,206,208,212,213,215,217,220,222,225,228,230,232,234,236,239,240,242,245,247,249,251,253,255,257,259,261,263,265,266,269,271,273,275,277,279,281,286,288,290,293],[50,38,38,194,11,32],"project\u002Fneutral\u002Fidea",[196,38,42,197,198,38],"23542377","project\u002Fpositive\u002Fidea","jfengel",[182,38,38,194,11,32],[201,38,32,202,203,38],"23542396","project\u002Fcritical\u002Fexecution","arcticfox",[185,38,38,205,11,32],"project\u002Fneutral\u002Fexecution",[113,38,33,207,114,38],"project\u002Fneutral\u002Fperformance",[209,38,38,210,211,38],"23542535","commenter\u002Fneutral\u002Fperformance","tixocloud",[53,38,38,207,11,32],[214,38,38,210,211,38],"23545543",[216,38,38,207,11,32],"23542619",[218,38,33,194,219,38],"23544040","amelius",[221,38,38,194,11,32],"23544435",[223,32,33,194,224,38],"23545559","denimboy",[226,32,38,227,11,32],"23546097","commenter\u002Fneutral\u002Fidea",[83,190,33,229,84,38],"project\u002Fneutral\u002Fnone",[160,190,38,231,11,32],"other\u002Fneutral\u002Fnone",[95,33,32,233,96,38],"project\u002Fcritical\u002Fidea",[102,30,33,235,103,38],"project\u002Fmixed\u002Fdesign",[237,30,38,238,11,32],"23548953","project\u002Fneutral\u002Fdesign",[122,42,33,238,123,38],[241,42,38,238,11,32],"23542635",[243,42,42,244,123,38],"23542763","project\u002Fpositive\u002Fdesign",[246,42,38,238,11,32],"23542792",[248,42,33,238,123,38],"23542880",[250,42,38,238,11,32],"23542971",[106,189,32,252,107,38],"project\u002Fcritical\u002Fdesign",[91,254,33,194,92,38],7,[256,254,38,194,11,32],"23542260",[258,254,38,227,92,38],"23542290",[260,254,38,194,11,32],"23543208",[262,254,38,227,92,38],"23544101",[136,264,33,238,137,38],8,[72,264,38,238,11,32],[267,264,42,268,137,38],"23562331","maker\u002Fpositive\u002Fnone",[270,264,38,238,11,32],"23566251",[166,272,33,194,167,38],9,[274,272,33,194,167,38],"23547665",[276,272,38,194,11,32],"23547990",[148,278,33,207,149,38],10,[280,278,38,207,11,32],"23546039",[282,283,42,284,285,38],"23558940",11,"project\u002Fpositive\u002Fnone","Kanamari",[129,287,33,238,130,38],12,[289,287,38,238,11,32],"23543612",[291,287,33,238,292,38],"23684858","nautist",[294,287,38,238,11,32],"23685431",[296,299,302,305],{"id":297,"t":298,"points":32,"comments":38},"22698348",1585259481,{"id":300,"t":301,"points":32,"comments":32},"23421940",1591305559,{"id":303,"t":304,"points":190,"comments":32},"23471065",1591737844,{"id":4,"t":12,"points":14,"comments":15},[307,312,317,322,326,331],{"id":308,"name":309,"points":310,"category":311},"23491940","Artvee",550,"learning_science",{"id":313,"name":314,"points":315,"category":316},"23519439","ISS Photo Explorer",528,"creative",{"id":318,"name":319,"points":320,"category":321},"23514682","Collected Notes",457,"productivity",{"id":323,"name":324,"points":325,"category":321},"23517394","LogoSearch",251,{"id":327,"name":328,"points":329,"category":330},"23549471","geekring",235,"consumer_social",{"id":332,"name":333,"points":334,"category":335},"23523830","Briefing",203,"infrastructure",false,"v2",{"id":339,"name":5,"line":6,"ai":336,"cat":20,"year":13,"points":14,"comments":15,"rec":27,"s":340,"top":18,"kw":341,"maker":11,"domain":10,"tier":19,"attempts":30,"strip":342,"url":9,"mix":343,"praise":79,"objection":88,"sub":21},23541840,-0.02,[21,24,25,26],"0501030003030301030503010000305330305303",[30,31,32,33],1794036592280]