@bArray really appreciate your feedback. Especially expansion opportunity.
DL model is trained on the GPU - heavy AWS instance..end point rests on smaller instance. Sometimes it gives faster results when you run a URL which it has already processed. It will happen in case of famous sites. For new sites it need to process the info so it takes about 10 seconds to create report.
When u meet someone all the time u start liking it. Our tool helps u get an average output that if u see someone for the very first time how much attractive u will find them. of course AI is not absolute but gives u some data points to u to decide. Thanks for your feedback.
Thanks for trying out. yes you are right. Tips are not upto the mark. Our algo tries to put a site in 8 buckets -b,..+A and provides tips. So it's not that accurate when evaluating 50% versus 53% but mostly accurate with difference of over 10%.. so 50% won't be same as 60% for example.. of course it is based on limited amount of data we had to guess it..point taken.. we really appreciate your feedback and will incorporate.. cool.
Agree that recco are not that upto the mark at the moment as it is just the first version...hence we called it tips. I appreaciate your feedback and thanks for trying ..
Yeas your's is militaristic...may be the algo though you have too much text..and no images so low visual appeal..may be a case we need to consider in the next training set..don't take the recommendation from algo on face value ..but just as a overall guidance..thanks for trying and sending over feedback.
Score is really base don the screenshot generated. If something is hidden behind the login system can't read it so will get error. We may in future have a functionality to upload ur own screenshot instead of taking it by machine. Thanks for the feedback.
Something must have went wrong. can you provide the site link. sometimes if some space is after the url while copy pasting can cause this error. Thanks for trying.
Hi, Thanks for your feedback you are right. Currently algo evaluate how a user will feel...when they look at your site above the fold...it's like tinder you just look at the pic and decide to swap right or left.. this is based on : Users make lasting judgments about a website’s appeal within a split second. This first impression is influential enough to later affect their opinions of a site’s usability and trustworthiness...of course lot of areas we can improve...hope u enjoyed..
yes u are right and thanks for the feedback. It's hard to say if you score is 72 out of 100 is it good very good or excellent.. we are just following what happens in the exam so 70% is good enough..not to be taken literally...moral of the story if score is above 60% the site is good...not to be taken as negative...
This algo only rates sites on how good visuals are not on utility. Google is a site where you go primarily for utility but ALGo says if you make your site like google only 38% of people are expected to like it.
Thanks for this really. I looked it and trust me AI has got this completely wrong ..we will include this as exception when we train again.. thanks for trying..
DL model is trained on the GPU - heavy AWS instance..end point rests on smaller instance. Sometimes it gives faster results when you run a URL which it has already processed. It will happen in case of famous sites. For new sites it need to process the info so it takes about 10 seconds to create report.