Banking and financial services

Data mapping

Entity

account or client

Group

branch or advisor

Profile

generic; configure time windows with verticals.register

Reference implementation

from datetime import datetime, timedelta
from vertiq import plugins, rules
from vertiq.mapping import Mapping, apply, repair
from vertiq.tasks import predict_event, predict_value

# rows: the source export as a list of dicts, e.g. list(csv.DictReader(open("export.csv")))
mapping = Mapping.parse({"entity": "Account No", "time": "Value Date", "type": "Txn Type", "value": "Amount", "group": "Branch", "attrs": ["Product", "Channel"], "date_format": "%d.%m.%Y"})
m, notes = repair(mapping, rows)      # validates column names, value types and date format against the rows
ds, problems = apply(m, rows)         # rows that fail to load are reported, not imputed

@plugins.feature("banking")
def debit_activity(entity, before, cut):   # receives only events recorded before the cutoff
    return {"debits_90": sum(1 for e in before if e.type == "DEBIT"
                          and e.at >= cut - timedelta(days=90))}

task = predict_event(ds, target="CREDIT", window_days=60, pack="banking")
print(task.status, task.report())     # "trained" only if the model outperformed the baseline on held-out entities
if task.status == "trained":
    print(task.score("AC-204118"))  # probability with contributing factors

flags = rules.run(ds, [
    rules.repeat(1, type="REVERSAL"),   # two reversals on one account in a day, for review
])
print(flags["summary"])

This code is executed by the test suite (tests/test_guides.py) against generated records with these column names.