Sachdeva: ShareChat Filters 100M Candidates Down to 10 per Feed
Ankush Sachdeva · How Have Indian Consumers Evolved In The Last 10 Years, Ankush Sachdeva, Founder, ShareChat and Moj · Jan 12, 2024 · at 48:46
Ankush Sachdeva, co-founder of ShareChat and Moj, explains the scale and candidate filtering mechanics of the apps' recommendation engine.
0:00 / 0:09exact quote · 9.1s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“Today, when you fetch a feed on shared chat and watch, we have about a hundred million candidates, from which we will find the 10, that you're most likely to complete the video watch.”
quote is from the automated transcript, cleaned for reading: filler sounds and stutters are removed, nothing is rephrased. names can be misheard (the analysis reads context, assessments check outside sources). how →
More from Ankush Sachdeva
Sachdeva: Non-English speaking Indians pick English app menus for aspiration
“They had no working vocabulary of English, they did not know the language, yet when given an option, they will pick that language. Because of aspirational reasons. And in fact, there was a lot of trust deficit. A lot of these regional language apps in the past…”
Sachdeva: The first profitable Bharat business will be social media
“So the first profitable Bharat business would actually be a social media business. If you think about it from that phase, right?”
Sachdeva: Delhi High Court ordered ByteDance to stop scraping ShareChat
“We in fact went to Delhi High Court. If you can Google ShareChat versus Hello or ByteDance. In fact, Delhi Highcore told, told them to not do this, not scrape, and in fact, change their app.”
Sachdeva: China Is Far Ahead of India in AI Recommender Systems
“Definitely. Definitely. There's no question about it. They're far more mature ecosystem to, like, in, in our narrow space of recommender systems, this is the specialization within AI, which we sort of work on, they're far ahead of India.”