Humach Finance: Fraud Triage
Work with rare-event detection, threshold trade-offs and cost-aware evaluation.
Download mini_finance.csvUse Python, SQL, Excel or your preferred workflow unless a task specifies otherwise.
Project dataset
Download CSVInspect the CSV before you answer the tasks
Scroll horizontally or vertically to examine the exact miniature data used by the validator.
| txn_id | amount | foreign | night | merchant_risk | fraud |
|---|---|---|---|---|---|
| T001 | 49 | 0 | 0 | 3 | 0 |
| T002 | 86 | 0 | 0 | 1 | 0 |
| T003 | 123 | 0 | 0 | 4 | 0 |
| T004 | 160 | 0 | 0 | 2 | 0 |
| T005 | 197 | 0 | 0 | 0 | 0 |
| T006 | 234 | 0 | 0 | 3 | 0 |
| T007 | 271 | 0 | 0 | 1 | 0 |
| T008 | 308 | 0 | 0 | 4 | 0 |
| T009 | 345 | 0 | 1 | 2 | 0 |
| T010 | 382 | 0 | 0 | 0 | 0 |
| T011 | 419 | 0 | 0 | 3 | 0 |
| T012 | 456 | 0 | 0 | 1 | 0 |
| T013 | 493 | 1 | 0 | 4 | 0 |
| T014 | 530 | 0 | 0 | 2 | 0 |
| T015 | 567 | 0 | 0 | 0 | 0 |
| T016 | 604 | 0 | 0 | 3 | 0 |
| T017 | 1841 | 0 | 0 | 1 | 1 |
| T018 | 678 | 0 | 1 | 4 | 0 |
| T019 | 715 | 0 | 0 | 2 | 0 |
| T020 | 752 | 0 | 0 | 0 | 0 |
| T021 | 789 | 0 | 0 | 3 | 0 |
| T022 | 826 | 0 | 0 | 1 | 0 |
| T023 | 863 | 0 | 0 | 4 | 1 |
| T024 | 900 | 0 | 0 | 2 | 0 |
| T025 | 37 | 0 | 0 | 0 | 0 |
| T026 | 74 | 1 | 0 | 3 | 0 |
| T027 | 111 | 0 | 1 | 1 | 0 |
| T028 | 148 | 0 | 0 | 4 | 0 |
| T029 | 185 | 0 | 0 | 2 | 0 |
| T030 | 222 | 0 | 0 | 0 | 0 |
| T031 | 259 | 0 | 0 | 3 | 0 |
| T032 | 296 | 0 | 0 | 1 | 0 |
| T033 | 333 | 0 | 0 | 4 | 0 |
| T034 | 1570 | 0 | 0 | 2 | 1 |
| T035 | 407 | 0 | 0 | 0 | 0 |
| T036 | 444 | 0 | 1 | 3 | 0 |
| T037 | 481 | 0 | 0 | 1 | 0 |
| T038 | 518 | 0 | 0 | 4 | 0 |
| T039 | 555 | 1 | 0 | 2 | 0 |
| T040 | 592 | 0 | 0 | 0 | 0 |
| T041 | 629 | 0 | 0 | 3 | 0 |
| T042 | 666 | 0 | 0 | 1 | 0 |
| T043 | 703 | 0 | 0 | 4 | 1 |
| T044 | 740 | 0 | 0 | 2 | 0 |
| T045 | 777 | 0 | 1 | 0 | 0 |
| T046 | 814 | 0 | 0 | 3 | 0 |
| T047 | 851 | 0 | 0 | 1 | 0 |
| T048 | 888 | 0 | 0 | 4 | 1 |
| T049 | 25 | 0 | 0 | 2 | 0 |
| T050 | 62 | 0 | 0 | 0 | 0 |
| T051 | 1299 | 0 | 0 | 3 | 1 |
| T052 | 136 | 1 | 0 | 1 | 0 |
| T053 | 173 | 0 | 0 | 4 | 0 |
| T054 | 210 | 0 | 1 | 2 | 0 |
| T055 | 247 | 0 | 0 | 0 | 0 |
| T056 | 284 | 0 | 0 | 3 | 0 |
| T057 | 321 | 0 | 0 | 1 | 0 |
| T058 | 358 | 0 | 0 | 4 | 0 |
| T059 | 395 | 0 | 0 | 2 | 0 |
| T060 | 432 | 0 | 0 | 0 | 0 |
Project workspace
Analyse → validate → submit.
Numeric and decision tasks are auto-checked. Written reasoning is checked for completeness and key ideas, then included in your local submission report.
0/5 validated
How many transactions are labelled fraud?
What is the largest transaction amount?
For rare fraud, which evaluation view is often more informative than accuracy alone?
Describe the business trade-off in lowering the fraud threshold.
Submit your project locally
HumachLearn stores no server-side data. Submission creates a portable JSON report containing your answers, validation state and timestamp.