> ## Documentation Index
> Fetch the complete documentation index at: https://developer.moneyone.in/llms.txt
> Use this file to discover all available pages before exploring further.
# Financial Insights and Analytics
> Transform raw financial data into actionable insights for underwriting, risk assessment, and personalization
## Overview
FinPro's Financial Insights and Analytics engine processes bank statements, transaction data, and financial information to extract meaningful patterns, calculate key metrics, and flag risk indicators. This capability enables Financial Information Users to make informed credit decisions, detect fraud, and personalize product offerings based on comprehensive financial behavior analysis.
## Core Features
### Transaction Categorization
The analytics engine automatically categorizes all incoming and outgoing transactions across 30+ predefined categories, enabling structured analysis of customer financial behavior.
#### Supported Categories
* **Salary**: Regular salary credits with 97% detection accuracy
* **Interest Credit**: Interest earned from savings accounts and deposits
* **Investment Income**: Returns from mutual funds, equities, and other investments
* **Cashback**: Reward credits from card transactions and promotional offers
* **Subsidy**: Government subsidies and benefit payments
* **Reversal Transactions**: Refunds and reversed debits
* **EMI**: Loan repayment installments including home, auto, and personal loans
* **Credit Card Payment**: Credit card bill payments and settlements
* **Rent**: Monthly rental payments and housing expenses
* **Utilities**: Electricity, water, gas, internet, and mobile bills
* **Shopping**: E-commerce and retail purchases
* **Food**: Restaurant, grocery, and food delivery expenses
* **Transportation**: Fuel, public transport, ride-sharing, and vehicle maintenance
* **Healthcare**: Medical expenses, pharmacy purchases, and insurance claims
* **Education**: Tuition fees, course payments, and educational expenses
* **Entertainment**: Movie tickets, streaming subscriptions, and leisure activities
* **Insurance Premium**: Life, health, vehicle, and other insurance payments
* **Donation**: Charitable contributions and religious offerings
* **Cash Deposit**: Cash deposits into accounts
* **Cash Withdrawal**: ATM and branch withdrawals
* **Transfer to/from Wallet**: Digital wallet loading and transfers
* **Transfer to FD/RD**: Fixed deposit and recurring deposit investments
* **Loan Disbursal**: Receipt of loan amounts from lenders
* **P2P Lending**: Peer-to-peer lending transactions
* **Investment Expense**: Purchase of financial instruments
* **Bank Charges**: Service fees, processing charges, and penalties
* **Minimum Balance Charge**: Penalties for not maintaining minimum balance
* **Bounced Charge**: Fees for bounced transactions
* **Tax Payment/Return**: Tax deductions and refunds
* **Alcohol**: Purchases from liquor stores and bars
* **Gambling**: Betting, lottery, and casino transactions
* **Gaming**: Online gaming and fantasy sports platforms
* **Bounced Transactions**: Failed payment attempts
* **Bounced Inward/Outward Cheque**: Dishonored cheques
* **Micro Finance**: Transactions with microfinance institutions
* **GST-related**: GST payments and refunds
* **CIBIL/Credit Bureau**: Credit report access fees
### Cumulative Analysis
The analytics engine consolidates financial data from multiple bank accounts to provide cross-institution insights that single-account analysis cannot deliver.
#### Key Cumulative Metrics
**Average End-of-Day (EOD) Balance**
Calculates the average closing balance across all linked accounts to assess overall liquidity and financial stability.
**Salary Trends**
Identifies salary credit patterns across accounts, detecting:
* Primary and secondary income sources
* Salary consistency and growth trends
* Irregular or missing salary payments
**Aggregate Cash Flow**
Computes total monthly inflows and outflows across all accounts, providing a complete picture of financial health.
**Multi-Bank Spending Patterns**
Analyzes combined spending across categories to identify lifestyle indicators and financial priorities.
### Recurring Pattern Detection
The system uses advanced pattern recognition algorithms to identify recurring credits and debits, which are critical indicators for income stability and spending habits.
#### Recurring Credits
* **Salary Detection**: Flags regular salary credits with metadata including employer name, credit date, and amount consistency
* **Rental Income**: Identifies periodic rental receipts for property owners
* **Investment Returns**: Detects recurring SIP returns, dividend credits, and interest payments
#### Recurring Debits
* **EMI Detection**: Identifies loan repayments with 97% accuracy, including loan type inference (home, auto, personal)
* **Subscription Services**: Flags recurring charges for streaming, software, utilities, and memberships
* **Insurance Premiums**: Detects periodic insurance payment patterns
### Salary and EMI Detection
FinPro's analytics engine employs machine learning models trained on millions of transactions to achieve market-leading accuracy in detecting salary credits and EMI debits.
#### Salary Detection (97% Accuracy)
The system identifies salary transactions by analyzing:
* **Transaction descriptions**: Pattern matching for keywords like "SAL", "SALARY", "PAYROLL", "NEFT SAL"
* **Amount consistency**: Tracking regular credit amounts within expected ranges
* **Frequency patterns**: Monthly or bi-weekly credit cycles
* **Source metadata**: Corporate account numbers and employer identifiers
**Output Includes:**
* Employer name (when identifiable)
* Monthly salary amount
* Credit date and frequency
* Salary consistency score
* Detected irregularities (late payments, amount changes)
#### EMI Detection (97% Accuracy)
The EMI detection algorithm identifies loan repayments by evaluating:
* **Transaction descriptions**: Keywords like "EMI", "LOAN", "INSTL", "INSTALLMENT"
* **Amount stability**: Fixed or decreasing EMI patterns
* **Lender identification**: Bank or NBFC identifiers
* **Repayment schedule**: Monthly debit cycles
**Output Includes:**
* Lender name
* EMI amount and frequency
* Estimated outstanding tenure
* Loan type inference (home, auto, personal, business)
* Repayment consistency and delays
### Custom Business Rules Engine
FinPro allows Financial Information Users to define proprietary underwriting logic and decision rules tailored to their specific use cases.
#### Rule Definition Capabilities
* **Conditional Logic**: Build if-then-else rules based on transaction data, balances, and calculated metrics
* **Mathematical Operations**: Compute FOIR (Fixed Obligation to Income Ratio), DBR (Debt Burden Ratio), and other custom ratios
* **Thresholds and Flags**: Set limits for risk indicators such as bounce frequency, cash withdrawal patterns, and minimum balance violations
* **Multi-Parameter Rules**: Combine multiple conditions across categories (e.g., high alcohol spend + frequent gambling + low savings)
#### Use Case Examples
**Credit Risk Scoring**
Create rules that assign credit scores based on:
* Salary consistency (regular vs irregular income)
* EMI burden as a percentage of income
* Savings rate (monthly surplus after expenses)
* High-risk transaction frequency
**Fraud Detection**
Flag suspicious patterns such as:
* Multiple small transactions followed by large withdrawals
* Sudden spikes in cash deposits
* Transactions on bank holidays
* Round-figure tax payments without corresponding income
**Product Personalization**
Offer targeted products based on:
* Investment activity (mutual fund buyers)
* Loan eligibility (low EMI burden, high salary)
* Insurance prospects (healthcare spending patterns)
* Premium services (high account balance, frequent travel)
## Integration Options
### Data Sources
FinPro's analytics engine can process financial data from multiple sources:
Real-time data fetched through consented AA journeys
Manual PDF statement uploads for offline analysis
GST returns and filings for business financial assessment
Investment portfolio data from registrars and depositories
Credit bureau data for comprehensive credit profiling
### API Access
Analytics results are accessible via RESTful APIs that return structured JSON responses with categorized transactions, computed metrics, and risk flags.
**Key API Endpoints:**
* `/fi/data` - Retrieve categorized transaction data
* `/fi/balance` - Access computed balance metrics
* `/analytics/summary` - Get aggregated financial insights
* `/analytics/risk-indicators` - Fetch irregularity and risk flags
## Irregularity and Risk Indicators
In addition to transaction-level analytics, the system detects suspicious patterns and risk flags that may indicate financial stress, fraud, or non-compliance.
### Detected Risk Indicators
* **Suspicious e-statements**: Detecting potential tampering or alterations
* **Round-figure tax payments**: Unusual tax payment patterns without corresponding income
* **Negative computed balances**: Calculated balances that don't match reported balances
* **Transactions on bank holidays**: Debits or credits occurring on non-working days
* **Higher frequency of cash deposits than salary inflows**: Suggesting unreported income sources
* **Large debit transactions immediately after salary credits**: Potential debt repayment or cash structuring
* **ATM withdrawals exceeding ₹20,000**: High cash usage patterns
* **Equal total debit and credit amounts**: Potential circular transactions
* **Bounced transactions**: Frequent payment failures indicating liquidity issues
* **Same party names in both credit and debit entries**: Potential circular money movement
* **Salary amount remains unchanged over extended periods**: Unusual income stability
* **Cheque deposits on bank holidays**: Suspicious deposit timing
### Use Cases for Risk Indicators
**Enhanced Fraud Detection**
Identify applicants engaging in income inflation, statement tampering, or circular transaction schemes.
**Deeper Risk Profiling**
Assess financial stress indicators such as frequent bounces, high cash dependency, and irregular income patterns.
**Sharper Underwriting**
Make informed lending decisions by combining traditional credit bureau data with behavioral risk flags derived from transaction analysis.
**Regulatory Compliance**
Flag potentially suspicious transactions that may require reporting under AML/CFT regulations.
## Outcomes and Benefits
### Faster Turnaround Time
Automated categorization and analytics reduce manual review effort, enabling faster credit decisions and customer onboarding.
### Unified Data Analytics
Consolidate insights from multiple data formats (AA, PDF, GST, CIBIL) into a single analytical framework for consistent decision-making.
### Enhanced Underwriting Capability
Leverage alternate data sources and behavioral insights to expand credit access while maintaining risk discipline.
### Improved Monitoring
Continuous analysis of recurring consents enables proactive risk management for loan portfolios and collections optimization.
### Personalized Experiences
Use financial behavior insights to tailor product recommendations, interest rates, and credit limits to individual customer profiles.
## Getting Started with Analytics
Retrieve bank statements or transaction data via AA consent or statement upload
Call the analytics API to categorize transactions and compute metrics
Configure business rules in the FinPro admin portal based on your underwriting criteria
Consume analytics results in your credit decisioning, PFM, or risk management systems
Explore Data Management and Analytics APIs
## Support
For questions about analytics configuration, custom rule creation, or integration support, contact the Moneyone technical team through the FinPro admin portal.