tag:blogger.com,1999:blog-5571562601269116541.post4928530420949632908..comments2023-09-21T07:48:54.666+05:30Comments on The Puzzling World of Logic: Carcinogenicity Prediction of CompoundsRohan Raohttp://www.blogger.com/profile/00426342915599780768noreply@blogger.comBlogger5125tag:blogger.com,1999:blog-5571562601269116541.post-15379818171446372082022-03-02T04:28:31.388+05:302022-03-02T04:28:31.388+05:30Thanks anyway!!!Thanks anyway!!!Anonymoushttps://www.blogger.com/profile/10409757501750117802noreply@blogger.comtag:blogger.com,1999:blog-5571562601269116541.post-28666577293895485272022-03-02T04:28:02.690+05:302022-03-02T04:28:02.690+05:30Hello Rohan, I am working on it theme today! Could...Hello Rohan, I am working on it theme today! Could you share the dataset from CPDB? I think the SMILES list with the compound is no more available..Anonymoushttps://www.blogger.com/profile/10409757501750117802noreply@blogger.comtag:blogger.com,1999:blog-5571562601269116541.post-27521278462155681372015-10-19T23:25:40.587+05:302015-10-19T23:25:40.587+05:30Thanks Rohan. This is really an eye-opener for me....Thanks Rohan. This is really an eye-opener for me. I tried some basic models at first and then gave up looking at your score and my score on the LB :D<br /><br />This is a very clever trick to outsmart the evaluation metric. Very good learning for me. Congratulations. :) Sudalai Rajkumarhttps://www.blogger.com/profile/17678121416218096589noreply@blogger.comtag:blogger.com,1999:blog-5571562601269116541.post-15956572682684929512015-10-06T17:42:04.223+05:302015-10-06T17:42:04.223+05:30Thanks Mark!
Nice to read your comment.
I struggl...Thanks Mark!<br />Nice to read your comment.<br /><br />I struggled with the Worker's Compensation on CAX :-(<br />Yes, its similar to the Loan Prediction one on Kaggle, and I'm glad it worked.<br /><br />Hope to see more such insights and competitions with wonderful models that change the landscape of Data Science in the future :-)Rohan Raohttps://www.blogger.com/profile/00426342915599780768noreply@blogger.comtag:blogger.com,1999:blog-5571562601269116541.post-15214970727014047452015-10-06T17:16:54.525+05:302015-10-06T17:16:54.525+05:30Congratulations on first place! Great post. I find...Congratulations on first place! Great post. I find this part of data science very interesting and under-appreciated.<br /><br />The worker's compensation CAX competition had similar characteristics to a large extent. I dropped my error 50% when my deep learning model correctly predicted a high-ranking claim and I multiplied its prediction by 10x. <br /><br />People like MSE because it's common and has convenient mathematical properties, but I agree that other metrics should be considered more often. Either that, or the some other method of framing the problem differently, including removing outliers beforehand. Hopefully the business host understands their goals well enough to know what they want optimized and data scientists can help structure the competition correctly to fit those goals.<br /><br />You probably remember this competition: https://www.kaggle.com/c/loan-default-prediction where two-stage classification/regression combinations were very popular. In that case it was MAE, which did reduce the impact of the high values, but the distribution still suggested an initial classifier would be useful. It's a fun technique when you can spot a problem that benefits, and your description here summarizes that well.<br /><br />Again, congratulations!Anonymoushttps://www.blogger.com/profile/14909834335800881357noreply@blogger.com