[{"data":1,"prerenderedAt":326},["ShallowReactive",2],{"project-27866289":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":33,"aspects":34,"strip":41,"post_text":43,"what":44,"said":56,"maker_in_thread":169,"shape":180,"grid":185,"attempts":282,"same_week":289,"maker_shows":30,"maker_hidden":318,"reader_version":319,"card":320},"27866289","Gorse","An Out-of-the-box open-source Recommender System","title","Show HN: Gorse – An Out-of-the-box open-source Recommender System","https:\u002F\u002Fgorse.io\u002F","gorse.io","zhenghaoz",1626534424,2021,212,41,211,2533,9,"notable","ai","recommender system","library",[21,24,25,26],"collaborative filtering","open source","matrix factorization","curious",-0.136,{"positive":30,"neutral":31,"mixed":30,"critical":32},1,10,3,15,{"design":35,"idea":37,"performance":38,"privacy":39,"docs":40},{"positive":36,"critical":30},0,{"positive":30,"critical":30},{"positive":36,"critical":30},{"positive":36,"critical":36},{"positive":36,"critical":36},[30,36,32,36,32,36,36,32,36,30,36,32,36,42,36,32,32,36,32,36,36,36,30,36,36,36,36,36,32,36,36,32,36,32,36,36,36,32,36,36],5,null,{"problem":43,"audience":45,"pricing":43,"motivation":43,"time_to_build":43,"stack":53,"openness":54,"stage":55,"team_size":55},{"value":46,"source":47,"evidence":48},"Product teams adding recommendations to their products","inferred",[49],{"id":50,"by":51,"text":52},"27867039","abeppu","I wonder whether a really good experience can be built by abstracting out recommendations to this degree. I think in the context of an actual product, there would be other…",[],"open_source","unknown",{"praise":57,"objections":66,"requests":86,"questions":124,"alternatives":145},[58],{"value":59,"source":60,"evidence":61},"Good project, automatic selection of best algorithm appreciated","commenter",[62],{"id":63,"by":64,"text":65},"27867074","Reubend","I think this looks very good, and I love seeing that it has the capability to automatically select the recommendation algorithm with the best performance. I think there are two…",[67,74,81],{"value":68,"source":60,"evidence":69},"Generic abstraction loses domain context such as contextual signals",[70,71],{"id":50,"by":51,"text":52},{"id":72,"by":11,"text":73},"27866961","There are no explicit negative feedback yet. When a item is seen by a user, the read event is recorded. If this user likes this item, the positive feedback is recorded. It seems…",{"value":75,"source":60,"evidence":76},"Popular items dominate recommendations, long tail suffers",[77],{"id":78,"by":79,"text":80},"27868633","vector_spaces","A challenge with naive recommender systems in an ecommerce setting is that they tend to recommend the most popular items on your site rather than surfacing the long tail of SKUs,…",{"value":82,"source":83,"evidence":84},"No explicit negative feedback","maker",[85],{"id":72,"by":11,"text":73},[87,98,105,116],{"value":88,"source":60,"evidence":89},"Real-time recommendations",[90,94],{"id":91,"by":92,"text":93},"27869121","KaoruAoiShiho","Does this handle real time recommendations as described here: https:\u002F\u002Feugeneyan.com\u002Fwriting\u002Freal-time-recommendations\u002F",{"id":95,"by":96,"text":97},"27870368","Mehdi2277","Contextual information is not the only reason. New content\u002Fnew users is the primary reason my current work place wants more real time recommendation especially when we mostly…",{"value":99,"source":60,"evidence":100},"Context-aware recommenders",[101],{"id":102,"by":103,"text":104},"27868153","antman","So are there any plans for context aware recommenders?",{"value":106,"source":60,"evidence":107},"Explicit negative feedback and dislikes",[108,112],{"id":109,"by":110,"text":111},"27866830","opheliate","Really interesting project, thank you for sharing! Looking at the documentation [0], it would appear that negative feedback for an item can only be given by giving feedback that…",{"id":113,"by":114,"text":115},"27868784","Sloppy","If you start with an algorithm that accepts any type of user behavior (is multimodal) then using user-dislikes is easy. We can easily do this with the Universal Recommender as…",{"value":117,"source":60,"evidence":118},"Documentation of algorithms and hyperparameter freezing",[119,123],{"id":120,"by":121,"text":122},"27868893","andyxor","cool project, i was curious which algorithms are used for recommendations\u002Franking, couldn't find it in the docs, so had to go through the code, may be add a section on algorithms…",{"id":63,"by":64,"text":65},[125,132,139],{"value":126,"source":60,"evidence":127},"Can it be used to build a local personal recommender?",[128],{"id":129,"by":130,"text":131},"27874446","Abishek_Muthian","Congratulations & Great work on the project! I just wrote in my problem validation platform about the need for personal recommendation system which can create a model based on…",{"value":133,"source":60,"evidence":134},"Will it be offered as a hosted service?",[135],{"id":136,"by":137,"text":138},"27867208","jedwhite","Great project! Are you thinking about offering this as a service as well? It feels like you could have a lot of interest with a run-it-yourself or we-do-it-for-you-as-a-service…",{"value":140,"source":60,"evidence":141},"Can graph databases be used?",[142],{"id":143,"by":92,"text":144},"27869147","What do you think about using a graph DB like neo4j, redis-graph or the chinese competitor Nebula Graph?",[146,155,162],{"value":147,"source":60,"evidence":148},"Universal Recommender \u002F Harness",[149,152],{"id":150,"by":114,"text":151},"27868742","The Universal Recommender (part of the Harness project) allows contextual and multimodal behavioral information to be used in recs. https:\u002F\u002Fgithub.com\u002Factionml\u002Fharness",{"id":153,"by":114,"text":154},"27868668","Apache PredictionIO was designed for data scientists (I was a committer so am quite familiar with design decisions). It was built to allow new \"engines\" to be implemented for any…",{"value":156,"source":60,"evidence":157},"Recombee",[158],{"id":159,"by":160,"text":161},"27867796","gingerlime","I use recombee[0] and it seems pretty nice, albeit not open source. Not affiliated in any way. Not even a paying customer, just using the free plan for a personal project. [0]…",{"value":163,"source":60,"evidence":164},"Apache PredictionIO",[165],{"id":166,"by":167,"text":168},"27868509","scoresmoke","Great job! Gorse reminds me of the now-retired Apache PredictionIO recommendation engine: https:\u002F\u002Fpredictionio.apache.org\u002Ftemplates\u002Frecommendation\u002Fquickstart\u002F. Have you evaluated…",{"comments":33,"answered":18,"key":170},[171,174,177],{"id":172,"text":173},"27867186","Your consideration is absolutely right. The abstractions in Gorse do lose lots of informations. Prior knowedges, contextual informations is important to further improve…",{"id":175,"text":176},"27867381","The problem is how to utilize these signals. The annoying thing is we can't solve these issues if we are not in this situation. So, feedbacks from Gorse users are important.",{"id":178,"text":179},"27869904","Once I collect context aware dataset, context aware recommenders could be implemented :)",{"commenters":181,"max_depth":182,"maker_replies":33,"first_comment_mins":183,"lifespan_hours":184},21,4,73,88,[186,188,190,194,195,197,198,200,201,203,207,208,211,214,216,218,220,221,224,227,229,231,233,235,238,242,245,247,250,252,253,257,260,263,266,269,271,274,275,277,280],[50,36,30,187,51,36],"project\u002Fcritical\u002Fdesign",[172,36,36,189,11,30],"maker\u002Fneutral\u002Fidea",[191,36,32,192,193,36],"27867275","project\u002Fneutral\u002Fdesign","barefeg",[175,36,36,189,11,30],[102,36,32,196,103,36],"project\u002Fneutral\u002Fidea",[178,36,36,189,11,30],[150,36,36,199,114,36],"other\u002Fneutral\u002Fnone",[109,30,32,192,110,36],[72,30,36,202,11,30],"maker\u002Fneutral\u002Fdesign",[204,30,30,205,206,36],"27867815","project\u002Fcritical\u002Fperformance","genewitch",[113,30,36,199,114,36],[63,209,32,210,64,36],2,"project\u002Fmixed\u002Fdesign",[212,209,36,213,11,30],"27867134","maker\u002Fneutral\u002Fnone",[129,32,42,215,130,36],"project\u002Fpositive\u002Fidea",[217,32,36,189,11,30],"27883037",[219,32,32,189,130,36],"27903024",[136,182,32,196,137,36],[222,182,36,223,11,30],"27867428","maker\u002Fneutral\u002Fprivacy",[225,182,32,226,137,36],"27867436","project\u002Fneutral\u002Fprivacy",[228,182,36,223,11,30],"27869821",[159,182,36,230,160,36],"other\u002Fpositive\u002Fnone",[232,182,36,213,11,30],"27869866",[78,42,30,234,79,36],"project\u002Fcritical\u002Fidea",[236,42,36,237,114,36],"27868763","other\u002Fneutral\u002Fidea",[239,42,36,240,241,36],"27868782","commenter\u002Fneutral\u002Fidea","contravariant",[243,42,36,237,244,36],"27868929","draugadrotten",[246,42,36,189,11,30],"27870249",[248,42,36,237,249,36],"27871490","janstice",[166,251,32,196,167,36],6,[153,251,36,237,114,36],[254,251,36,255,256,36],"27879869","commenter\u002Fneutral\u002Fnone","jesterson",[120,258,32,259,121,36],7,"project\u002Fneutral\u002Fdocs",[261,258,36,262,11,30],"27869804","maker\u002Fneutral\u002Fdocs",[91,264,32,265,92,36],8,"project\u002Fneutral\u002Fperformance",[267,264,36,268,11,30],"27869913","maker\u002Fcritical\u002Fperformance",[95,264,36,270,96,36],"other\u002Fneutral\u002Fperformance",[272,264,36,273,11,30],"27872518","maker\u002Fneutral\u002Fperformance",[143,18,32,192,92,36],[276,18,36,202,11,30],"27869846",[278,31,36,199,279,36],"27869472","darknavi",[281,31,36,213,11,30],"27869793",[283,288],{"id":284,"t":285,"points":286,"comments":287},"21644570",1574818814,76,18,{"id":4,"t":12,"points":14,"comments":15},[290,295,299,303,308,313],{"id":291,"name":292,"points":293,"category":294},"27871790","CheckYourList",282,"productivity",{"id":296,"name":297,"points":298,"category":294},"27893303","Sioyek",272,{"id":300,"name":301,"points":302,"category":294},"27853855","Deprocrastination",214,{"id":304,"name":305,"points":306,"category":307},"27882355","Should I Get a House?",203,"finance_crypto",{"id":309,"name":310,"points":311,"category":312},"27894903","WrittenRealms",200,"games",{"id":314,"name":315,"points":316,"category":317},"27900862","Hacker News",188,"consumer_social",false,"v2",{"id":321,"name":5,"line":6,"ai":318,"cat":20,"year":13,"points":14,"comments":15,"rec":27,"s":322,"top":18,"kw":323,"maker":11,"domain":10,"tier":19,"attempts":209,"strip":324,"url":9,"mix":325,"praise":59,"objection":68,"sub":21},27866289,-0.14,[21,24,25,26],"1030300301030503303000100000300303000300",[30,31,30,32],1794036609115]