liveBook · Manning

Retention

As explained in Financial AI in Practice

Retention is the proportion or number of users who continue using a product or service over a specified period.

Retention measures whether users continue using a financial product over time. It is a stronger success signal than clicks alone: sustained use should reflect trust and useful support, not pressure to trade. section 13.1.1 section 13.4.1

Evaluate retention in context:

  • Check whether users return the following month after receiving context-aware recommendations. section 13.4.1
  • Compare whole feeds, such as generic and context-aware feeds, rather than judging individual articles. section 13.4.1
  • Pair retention with measures such as net inflows, portfolio concentration, and panic-driven behavior; clicks alone do not establish financial success. section 13.4.1

A stabilizing recommendation

For users trading aggressively under stress, assess whether stabilizing information is followed by lower churn or fewer forced liquidations. Treat these as outcome checks, not proof that retention alone captures user welfare. section 13.4.1

How Financial AI in Practice covers it

How deep it goes
Evaluates return behavior over time and alongside financial-stability outcomes.
Examples
Uses next-month returns, stressed-user churn, and forced liquidations as concrete checks.
What you can do after
Evaluate context-aware feeds using retention alongside net inflows and portfolio concentration.
How it connects
Connects retention with click-through rate, A/B testing, and personalization.

Also explained in

Compare how 7 books explain retention →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Financial AI in Practice. The section links point to the parts of the book it draws on.