581–590 of 600 posts
Two years ago we built this tool https://imagetranslate.com to translate and recreate images such as banners, advertisements, brochures etc. It is being used by individuals as of now. (freelance translators, marketers, ecomm resellers) . But we wanted to integrate it with a bigger localisation tool as it would be of much more value for their day to day translation jobs. We couldn't close a deal there.
I assume you are using machine translation on the backend?
It used a genetic algorithm to generate the pairings and handled all the messaging so the organiser was also kept in the dark about who got who.
I slapped an Amazon ad on there and it worked great, but I never bothered marketing it so it got very little usage and eventually I took it down when shutting down an old server.
I learnt a lot about mysql and genetic algorithms, both of which I've gone on to use extensively in my job so it was well worth it overall, just sad it didn't generate a bit of passive income :/
Late 2019, I launched https://stocks2.com , a financial site that posts a daily updated report for all NASDAQ/NYSE stocks. It started well, increasingly growing audience and Adsense revenues until Google's May 2020 core update. Since then, the site started sliding in the SERPs and finally it now disappeared from Google. Honestly, I still don't understand why Google has penalized the site so much. Any feedback will be…
Searching for a symbol is not pulling any data. There is no audit info on the page like contact, address, team etc How many page views do you have?
I built a really simple way to poll 50 random people in the US. It's called This or That and functionality is currently very simple. You submit a question along with two images via SMS and you get your answer back usually within the hour. I've had a few people use to test new logo ideas, to ask which of two TV shows to watch, or which outfit looks best. So far no one has paid for it, only a few hundred free users, bu…
Make it useable by asking people to answer questions in exchange for getting to ask their own question? Reaching critical mass may be harder, but I think it would be more random than mechanical turk.
You can also charge people for the ability to ask a follow up question like why they made the decision they did.
Earlier quoted context omitted.
Nice! Do you mind elaborating more on how you went about training your models, where do you generate the outputs (web page? spreadsheet?), and the difficulties you encountered or the tedious/repetitive parts?
I downloaded and have curated historical sports data from various sources and figured out the 'simplest' parameters which work.. which at the moment is just the defaults. Model training is not much to be honest. I have a fairly fast processor so it takes about 10 minutes to run every iteration. It has evolved from predicting just one dimension/feature but now, it predicts all of the variables it can train on (all tra…
Are you using Jupyter notebooks? Are you saving the model and how?
>That part can be optimised via web scraping but not a priority at the moment but is a priority nevertheless.
Are you doing this manually right now instead of a script?
>Outputs are generated into a spreadsheet at the moment but would publish them onto an online platform later once I figure out the 'monetizing' and user-prompted running of the algorithim part.
What decisions do the results in the spreadsheet inform or what actions do they trigger? How would I, as a consumer, use these results?
It's feature complete, but I need more people to beta test it to see if the flow works or not. Check out www.threefiveapp.com and fill in your email if you are interested.
Earlier quoted context omitted.
I downloaded and have curated historical sports data from various sources and figured out the 'simplest' parameters which work.. which at the moment is just the defaults. Model training is not much to be honest. I have a fairly fast processor so it takes about 10 minutes to run every iteration. It has evolved from predicting just one dimension/feature but now, it predicts all of the variables it can train on (all tra…
> Model training is not much to be honest. Are you using Jupyter notebooks? Are you saving the model and how? > That part can be optimised via web scraping but not a priority at the moment but is a priority nevertheless. Are you doing this manually right now instead of a script? > Outputs are generated into a spreadsheet at the moment but would publish them onto an online platform later once I figure out the 'monetiz…
Earlier quoted context omitted.
> current Tech giants are need to be replaced There's no reason their replacement will be any more moral. They should be dismantled imho.
Should the tech giants really be punished for being too successful? I don't think so. They got to their size by being better. Nobody thought yahoo would ever be unseated. Yawho?
Wrote an addin for Excel which offloaded workbook computation to the GPU for about 10-20x speed improvement. Posted a video demo on YouTube and keep getting the few odd messages once a month asking if it’s available for sale but I’m still clueless on how to properly validate whether it’ll sell. To make it a complete product would require a lot of time which I don’t have right now