Aprenda Automating Compliance Checks | Automation and Fraud Detection in Banking

In banking, compliance requirements are designed to prevent illegal activities such as money laundering, terrorist financing, and fraud. Regulatory bodies require banks to monitor transactions for suspicious patterns, including unusually large transfers or activity involving high-risk countries. Manual compliance checks are time-consuming and prone to error. As transaction volumes increase, automating these checks becomes essential for efficiency, consistency, and meeting regulatory obligations.


              123456789101112131415161718192021222324
            
import pandas as pd

# Example transaction data
data = {
    "transaction_id": [1, 2, 3, 4, 5],
    "amount": [500, 12000, 300, 25000, 150],
    "country": ["US", "IR", "FR", "RU", "US"]
}
df = pd.DataFrame(data)

# List of high-risk countries
high_risk_countries = ["IR", "RU", "KP", "SY"]

def flag_transaction(row, threshold=10000):
    if row["amount"] > threshold:
        return "Large Transaction"
    elif row["country"] in high_risk_countries:
        return "High-Risk Country"
    else:
        return "OK"

# Apply the flagging function to each transaction
df["compliance_flag"] = df.apply(flag_transaction, axis=1)
print(df)

Applying compliance checks at scale requires working with entire datasets, often stored in DataFrames. By using the apply method, you can efficiently run custom flagging functions on every transaction. This allows you to automatically identify and label transactions that require further review. After flagging, you can generate compliance reports by filtering and summarizing the flagged transactions, providing auditors and regulators with clear, actionable insights.


              1234567
            
# Generate a summary report of flagged transactions
flagged = df[df["compliance_flag"] != "OK"]
report = flagged.groupby("compliance_flag").agg(
    count=("transaction_id", "count"),
    total_amount=("amount", "sum")
)
print(report)

Tudo estava claro?

Obrigado pelo seu feedback!

Seção 3. Capítulo 6

Pergunte à IA

Pergunte o que quiser ou experimente uma das perguntas sugeridas para iniciar nosso bate-papo

Deslize para mostrar o menu


              123456789101112131415161718192021222324
            
import pandas as pd

# Example transaction data
data = {
    "transaction_id": [1, 2, 3, 4, 5],
    "amount": [500, 12000, 300, 25000, 150],
    "country": ["US", "IR", "FR", "RU", "US"]
}
df = pd.DataFrame(data)

# List of high-risk countries
high_risk_countries = ["IR", "RU", "KP", "SY"]

def flag_transaction(row, threshold=10000):
    if row["amount"] > threshold:
        return "Large Transaction"
    elif row["country"] in high_risk_countries:
        return "High-Risk Country"
    else:
        return "OK"

# Apply the flagging function to each transaction
df["compliance_flag"] = df.apply(flag_transaction, axis=1)
print(df)


              1234567
            
# Generate a summary report of flagged transactions
flagged = df[df["compliance_flag"] != "OK"]
report = flagged.groupby("compliance_flag").agg(
    count=("transaction_id", "count"),
    total_amount=("amount", "sum")
)
print(report)

Tudo estava claro?

Obrigado pelo seu feedback!

Seção 3. Capítulo 6

Automating Compliance Checks

1. What is the benefit of automating compliance checks in banking?

2. How can Python help generate compliance reports?

3. Which DataFrame method is useful for applying a function to each row?

Automating Compliance Checks

1. What is the benefit of automating compliance checks in banking?

2. How can Python help generate compliance reports?

3. Which DataFrame method is useful for applying a function to each row?