The Netflix Prize Paradox: When a Better Algorithm Creates a Worse User Experience

    In 2006, Netflix announced a challenge: improve our recommendation algorithm by 10%, win $1 million. The Netflix Prize became one of the most famous machine learning competitions ever. Thousands of teams from around the world competed for three years. In 2009, team “BellKor’s Pragmatic Chaos” won. They’d built an algorithm that was 10.06% better than Netflix’s existing system. Netflix awarded the $1 million prize. The press celebrated the triumph of data science. ...

    February 1, 2025 · 7 min · Rafiul Alam

    Variable Rewards: The Psychology Behind Addictive Apps

    I checked Twitter 47 times yesterday. Not because I needed information. Not because I was expecting something important. Just… checking. Pull down to refresh. Scan. Nothing interesting. Close app. Five minutes later: Open app. Pull down to refresh. Scan. Find one mildly interesting tweet. Read. Close app. Repeat. All day. I wasn’t looking for something specific. I was looking for the possibility of something interesting. And that’s exactly how Twitter (and every other addictive app) is designed to work. ...

    July 29, 2024 · 13 min · Rafiul Alam