Data quality
Handling missing values
Notice empty or placeholder values and choose between completing, flagging or excluding them.
A value can be missing openly (an empty cell) or in disguise: “N/A”, “0”, “1900-01-01”, “unknown”. Handling missing values means spotting both kinds and understanding why the data is absent.
Missing values are rarely random. If income is often missing for one type of customer, filling the gaps with the average or ignoring those rows biases every analysis built on top, and a model trained on that data repeats the bias.
The right response depends on the case: complete the value from a reliable source, flag it as missing, or leave the record out and say so. Filling a gap with a plausible guess, without saying so, is the option to avoid.
In the reports of your games, every answer linked to this skill counts: the skill is shown as acquired from 80% of correct answers, and in progress from 50%.
Games that train this skill
Play them for free, without an account, then adapt them for your teams.
