Цели и метрики рекомендательной ленты в банковском приложении
Цели и метрики рекомендательной ленты в банковском приложении
Ответить самому
Сначала сформулируйте ответ как на собеседовании, затем откройте разбор и оцените себя.
Короткий ответ
Clarify the business objective first: retention, loyalty and time spent, not ad revenue. Then define engagement metrics plus guardrails for quality, safety, fatigue and downstream banking experience.
Полный разбор
Start from product intent. If the feed is not monetized by ads, the recommender should support retention, app engagement, loyalty and cross-product trust rather than pure click maximization. This changes the metric set.
Primary metrics can include sessions with feed, dwell time, return rate, meaningful interactions, likes, comments, shares, follows and bookmarks. But each engagement metric is gameable. Use guardrails such as hide/report rate, low-quality content rate, repeated-topic fatigue, notification churn, creator concentration, latency and impact on core banking journeys.
Define the decision surface too: ranking posts in a feed for about millions of users, hundreds of thousands of historical posts and a steady inflow of new posts. That scope determines freshness, cold-start and serving constraints.
Теория
MLSD starts with the product decision and metric contract; otherwise the model may optimize the wrong behavior.
Типичные ошибки
- Start with a model before defining why the feed exists.
- Use only clicks for a social feed.
- Forget safety and trust guardrails in a bank app.
- Ignore baseline logs and current product behavior.
Как отвечать на собеседовании
- Say what is not the goal, especially ad revenue in this prompt.
- Pair every engagement metric with at least one guardrail.