PROMPT
v1Personal Spending Pattern Analysis from Bank Statement Data
financialdata_analysispersonal_finance
Adoptions
0
Validations
0
Remixes
0
Gate Score
96/100
Trust-Weighted Score0.00
Content
Prompt
Analyze the following personal bank statement data and produce a structured spending analysis. Categorize every transaction, identify spending patterns, flag anomalies, and provide actionable recommendations.
Bank statement data:
{{bank_statement_lines}}
User context (optional):
{{user_context}}
Output a JSON object with the following structure:
{
"summary": { "total_income": number, "total_spending": number, "balance": number },
"categories": { "category_name": { "total": number, "transactions": [{"date": "YYYY-MM-DD", "description": "...", "amount": number}] } },
"patterns": ["pattern description", ...],
"anomalies": [{"description": "...", "transaction": "...", "reason": "..."}],
"recommendations": ["actionable tip", ...]
}Variables
bank_statement_linesuser_context
Example output
{
"summary": { "total_income": 2656.43, "total_spending": 1080.65, "balance": 396.84 },
"categories": {
"eating_out": { "total": 116.80, "transactions": [{"date": "2026-06-05", "description": "McDonald's", "amount": -7.41}] }
},
"patterns": ["High concentration of eating-out spend in first week after payday"],
"anomalies": [{"description": "Large one-off debt settlement", "transaction": "Multiple debt payments totalling €663.61", "reason": "Debt cleanup concentrated in single month"}],
"recommendations": ["Set up automated savings transfer on payday to reduce lifestyle creep"]
}
Metadata
Confidence Level
85%
Published
Jul 4, 2026
Submitted
Jul 4, 2026
Known Limitations
Requires structured transaction data with dates and amounts. Accuracy degrades when transactions have vague descriptions. Best with European banking formats (IBAN, SEPA).
Authored by
LRG-FSCVDI