[{"data":1,"prerenderedAt":233},["ShallowReactive",2],{"project-2134433":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":28,"sentiment":29,"stance_mix":30,"scored_comments":34,"aspects":35,"strip":41,"post_text":44,"what":45,"said":48,"maker_in_thread":144,"shape":146,"grid":150,"attempts":195,"same_week":196,"maker_shows":42,"maker_hidden":225,"reader_version":226,"card":227},"2134433","EDW","EDW, quantitative analytics, machine learning.","title","Show HN: EDW, quantitative analytics, machine learning.","http:\u002F\u002Fblog.mediafederation.com\u002Fandy-hawkins\u002Fthe-edward-worthington-project\u002F","blog.mediafederation.com","a904guy",1295848895,2011,70,18,177,1097,17,"notable","finance_crypto","algorithmic trading","web_app",[24,25,26,27],"quantitative trading","backtesting","machine learning","stock trading","roasted",-0.143,{"positive":31,"neutral":31,"mixed":32,"critical":33},2,0,4,8,{"execution":36,"idea":38,"performance":39,"design":40},{"positive":32,"critical":37},1,{"positive":32,"critical":37},{"positive":32,"critical":31},{"positive":31,"critical":32},[37,37,32,37,32,42,43,32,43,32,32,32,32,32,42,37,32,32],3,5,null,{"problem":44,"audience":44,"pricing":44,"motivation":44,"time_to_build":44,"stack":46,"openness":47,"stage":47,"team_size":47},[],"unknown",{"praise":49,"objections":62,"requests":96,"questions":111,"alternatives":131},[50],{"value":51,"source":52,"evidence":53},"Demo web interface looks impressive and is worth a look","commenter",[54,58],{"id":55,"by":56,"text":57},"2134508","copper","Since this article doesn't mention it clearly, the demo is really nice, and worth a look: http:\u002F\u002Fedwardworthington.com\u002F",{"id":59,"by":60,"text":61},"2134497","aothman","Looks impressive, particularly if those are real trading results. One concern I immediately have is overfitting, particularly for claims about how various difficult values have…",[63,75,83,89],{"value":64,"source":52,"evidence":65},"Reported 92% trade success rate suggests in-sample backtesting and overfitting",[66,70,74],{"id":67,"by":68,"text":69},"2135647","cschmidt","Looking at the web interface, it is claiming a 92% success rate on trades. That clearly indicates to me that those results are \"in-sample\". In other words, the model was trained…",{"id":71,"by":72,"text":73},"2135668","ajays","Yep, it's the same thing as \"testing on the training set\". With memorization, one can achieve almost 100% on the training set. I'm not saying that EDW is doing this, but I'd be…",{"id":59,"by":60,"text":61},{"value":76,"source":52,"evidence":77},"No mention of transaction costs or slippage",[78,79],{"id":67,"by":68,"text":69},{"id":80,"by":81,"text":82},"2134681","b0b0b0b","When modelling hypothetical trades do you account for slippage and transaction costs?",{"value":84,"source":52,"evidence":85},"Closed source, so results are hard to verify",[86],{"id":87,"by":72,"text":88},"2134503","This looks interesting. Even though it's closed-source, the architecture is interesting. As an amateur, I'm always stymied by the lack of data. For intra-day trading, where do…",{"value":90,"source":52,"evidence":91},"Large drawdowns in the P&L sheet",[92],{"id":93,"by":94,"text":95},"2134594","spitfire","If you look at his P&L sheet he has some largish drawdowns, with a lot of neutralish trades. I'd prefer to see smaller, but more consistent wins.",[97,104],{"value":98,"source":52,"evidence":99},"Explain the machine learning method and whether test data is separate from training data",[100],{"id":101,"by":102,"text":103},"2134787","dododo","if you use some kind of regularization (e.g., if you think the parameters are sparse) it's possible to fit to such a large space without overfitting. this is common in machine…",{"value":105,"source":52,"evidence":106},"Show risk-oriented portfolio construction and alpha calculation",[107],{"id":108,"by":109,"text":110},"2134562","joshu","I accidentally down voted but meant to up vote. I agree. Also, this appears to have no risk-oriented portfolio construction. You are calculating alphas somewhere, right? (not to…",[112,120,127],{"value":113,"source":52,"evidence":114},"Where does the intraday data come from?",[115,116],{"id":87,"by":72,"text":88},{"id":117,"by":118,"text":119},"2135341","lrm242","There is data everywhere, and a lot of it is crap. Before you ask yourself what kind of data you need, you must ask yourself what kind of models you want to build. You can buy…",{"value":121,"source":52,"evidence":122},"Why year-to-date and month-to-date values do not match, and why liquid equity exceeds account value",[123],{"id":124,"by":125,"text":126},"2134593","benmccann","Why don't the values for year-to-date and month-to-date match? Is it a fake mock or a bug? Why is Liquid Equity significantly greater than Account Value? Is it another fake mock…",{"value":128,"source":52,"evidence":129},"Does the model account for slippage and transaction costs?",[130],{"id":80,"by":81,"text":82},[132,136,140],{"value":133,"source":52,"evidence":134},"Exchange depth-of-book data feeds (NASDAQ ITCH, NYSE ArcaBook)",[135],{"id":117,"by":118,"text":119},{"value":137,"source":52,"evidence":138},"Nanex NxCore tick data",[139],{"id":117,"by":118,"text":119},{"value":141,"source":52,"evidence":142},"Interactive Brokers market data",[143],{"id":117,"by":118,"text":119},{"comments":32,"answered":32,"key":145},[],{"commenters":147,"max_depth":33,"maker_replies":32,"first_comment_mins":148,"lifespan_hours":149},14,39,11,[151,153,155,157,159,161,163,165,169,170,172,174,176,178,183,186,187,191],[59,32,37,152,60,32],"project\u002Fcritical\u002Fexecution",[108,32,37,154,109,32],"project\u002Fcritical\u002Fidea",[101,32,32,156,102,32],"commenter\u002Fneutral\u002Fexecution",[67,37,37,158,68,32],"project\u002Fcritical\u002Fperformance",[71,37,32,160,72,32],"commenter\u002Fneutral\u002Fperformance",[124,31,42,162,125,32],"project\u002Fneutral\u002Fexecution",[55,42,43,164,56,32],"project\u002Fpositive\u002Fdesign",[166,33,32,167,168,32],"2134644","commenter\u002Fneutral\u002Fnone","michael_dorfman",[87,43,43,164,72,32],[171,43,32,167,56,32],"2134563",[173,43,32,167,72,32],"2134676",[175,43,32,167,109,32],"2134771",[117,43,32,177,118,32],"other\u002Fneutral\u002Fnone",[179,180,32,181,182,32],"2134631",6,"other\u002Fcritical\u002Fidea","gaspard",[80,184,42,185,81,32],7,"project\u002Fneutral\u002Fperformance",[93,34,37,158,94,32],[188,189,32,177,190,32],"2134648",9,"chr15",[192,193,32,177,194,32],"2135483",10,"chopsueyar",[],[197,202,207,212,216,221],{"id":198,"name":199,"points":200,"category":201},"2131563","Fqwiki",96,"learning_science",{"id":203,"name":204,"points":205,"category":206},"2128752","WerdMerge",71,"languages",{"id":208,"name":209,"points":210,"category":211},"2122199","Punchd",52,"consumer_social",{"id":213,"name":214,"points":215,"category":211},"2132357","ioswebdevmusings.blogspot.com",48,{"id":217,"name":218,"points":219,"category":220},"2142085","Fireworks Mobile",38,"dev_tools",{"id":222,"name":223,"points":224,"category":211},"2133040","My first MVP",24,false,"v2",{"id":228,"name":5,"line":6,"ai":225,"cat":20,"year":13,"points":14,"comments":15,"rec":28,"s":229,"top":18,"kw":230,"maker":11,"domain":10,"tier":19,"attempts":32,"strip":231,"url":9,"mix":232,"praise":51,"objection":64,"sub":21},2134433,-0.14,[24,25,26,27],"110103505000003100",[31,31,32,33],1793990870336]