aj/MoneyMap
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add intelligent word-based merchant matching for receipt mapping

Browse Source 
Implemented word-based relevance scoring to intelligently sort transactions when multiple matches exist within the amount tolerance. The system now:

1. Splits receipt merchant name into words (handling spaces, dashes, underscores, dots)
2. Compares each word against transaction merchant name and transaction name
3. Scores based on matching word count (bidirectional substring matching)
4. Exact matches get highest priority (score 1000)
5. Word matches get scored (10 points per matching word)
6. Sorts by relevance score, then by date

Examples:
- Receipt "Duke Energy" matches "DUKE ENERGY CORPORATION" better than "WALMART"
- Receipt "McDonald's" matches "MCDONALD'S #12345" better than "BURGER KING"
- Receipt "Comcast" matches "COMCAST CABLE" better than "VERIZON"

This dramatically improves auto-mapping success rate and puts the most likely transaction at the top of the manual selection list.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
AJ
2025-10-12 19:33:47 -04:00
parent c7089dba98
commit fa142288b6
2 changed files with 41 additions and 23 deletions
Download Patch File Download Diff File Expand all files Collapse all files

26
MoneyMap/Pages/Receipts.cshtml.cs
View File

@@ -254,32 +254,30 @@ namespace MoneyMap.Pages
var candidates = await query
.ToListAsync();
// If receipt has merchant, sort matches by relevance (but don't exclude)
// Sort by merchant/name relevance using word matching
if (!string.IsNullOrWhiteSpace(receipt.Merchant))
{
var merchantLower = receipt.Merchant.ToLower();
var receiptWords = receipt.Merchant.ToLower().Split(new[] { ' ', '-', '_', '.' }, StringSplitOptions.RemoveEmptyEntries);
// Sort: exact matches first, then partial matches, then others
candidates = candidates
.OrderByDescending(t =>
{
var merchantName = t.Merchant?.Name?.ToLower() ?? "";
var transactionName = t.Name?.ToLower() ?? "";
// Exact match on merchant or transaction name
if (merchantName == merchantLower || transactionName == merchantLower)
return 3;
// Exact match
if (merchantName == receipt.Merchant.ToLower() || transactionName == receipt.Merchant.ToLower())
return 1000;
// Contains match on merchant
if (merchantName.Contains(merchantLower))
return 2;
// Count matching words
var merchantWords = merchantName.Split(new[] { ' ', '-', '_', '.' }, StringSplitOptions.RemoveEmptyEntries);
var transactionWords = transactionName.Split(new[] { ' ', '-', '_', '.' }, StringSplitOptions.RemoveEmptyEntries);
// Contains match on transaction name
if (transactionName.Contains(merchantLower))
return 1;
var merchantMatches = receiptWords.Count(rw => merchantWords.Any(mw => mw.Contains(rw) || rw.Contains(mw)));
var transactionMatches = receiptWords.Count(rw => transactionWords.Any(tw => tw.Contains(rw) || rw.Contains(tw)));
// No match
return 0;
// Return the higher match count
return Math.Max(merchantMatches * 10, transactionMatches * 10);
})
.ThenByDescending(t => t.Date)
.ThenByDescending(t => t.Id)

38
MoneyMap/Services/ReceiptAutoMapper.cs
View File

@@ -118,18 +118,38 @@ namespace MoneyMap.Services
return new List<Transaction>();
}
// Filter by merchant if available
if (!string.IsNullOrWhiteSpace(receipt.Merchant))
{
// Try to find matching merchant name
query = query.Where(t =>
(t.Merchant != null && t.Merchant.Name.Contains(receipt.Merchant)) ||
t.Name.Contains(receipt.Merchant));
}
// Get candidates
var candidates = await query.ToListAsync();
// Sort by merchant/name relevance using word matching if merchant available
if (!string.IsNullOrWhiteSpace(receipt.Merchant))
{
var receiptWords = receipt.Merchant.ToLower().Split(new[] { ' ', '-', '_', '.' }, StringSplitOptions.RemoveEmptyEntries);
candidates = candidates
.OrderByDescending(t =>
{
var merchantName = t.Merchant?.Name?.ToLower() ?? "";
var transactionName = t.Name?.ToLower() ?? "";
// Exact match
if (merchantName == receipt.Merchant.ToLower() || transactionName == receipt.Merchant.ToLower())
return 1000;
// Count matching words
var merchantWords = merchantName.Split(new[] { ' ', '-', '_', '.' }, StringSplitOptions.RemoveEmptyEntries);
var transactionWords = transactionName.Split(new[] { ' ', '-', '_', '.' }, StringSplitOptions.RemoveEmptyEntries);
var merchantMatches = receiptWords.Count(rw => merchantWords.Any(mw => mw.Contains(rw) || rw.Contains(mw)));
var transactionMatches = receiptWords.Count(rw => transactionWords.Any(tw => tw.Contains(rw) || rw.Contains(tw)));
// Return the higher match count
return Math.Max(merchantMatches * 10, transactionMatches * 10);
})
.ThenByDescending(t => t.Date)
.ToList();
}
// If we have a total amount, filter by amount match (±10% tolerance)
if (receipt.Total.HasValue)
{