Timeline for Been stuck on a DS problem. Just need to know whether this problem statement is solvable or not
Current License: CC BY-SA 4.0
7 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jul 30, 2023 at 17:48 | answer | added | Lucas Morin | timeline score: 0 | |
| Jul 29, 2023 at 8:56 | review | Close votes | |||
| Aug 13, 2023 at 3:05 | |||||
| Jul 25, 2023 at 5:54 | answer | added | noNameTed | timeline score: 1 | |
| Jul 23, 2023 at 14:42 | comment | added | Broele |
What I would change: build a model with continuous output (like predict_proba in sklearn). Then you can build a policy / rule closely along your business expertise to decide between automatic approval and manual processing. This can be done purely based on the probability (e.g. in a way, that only 5% are processed manually), but you could also include expected loss (risk-probability x active-sourcing-cost) into such a policy.
|
|
| Jul 23, 2023 at 14:38 | comment | added | Broele | To my understanding, the real question is either, whether to approve someone or - even more accurate - whether someone defaults. Both questions would lead in a similar direction as your alternate solution. | |
| Jul 23, 2023 at 13:23 | comment | added | monte | I presume you already tried this, but what does EDA say about maximum allowed? You can't take 90% quantile of purchase made by users in past as maximum allowed? I would take business into confidence if that value makes sense from the business point of view and logically. | |
| Jul 23, 2023 at 4:52 | history | asked | Aakash Dusane | CC BY-SA 4.0 |