Intelligent Routing System

Route every ticket to the right team

TF-IDF powered multiclass classification that automatically triages incoming support tickets — fast, interpretable, and production-ready.

Custom designed for banking systems using the banking77 dataset from HuggingFace.

95%
Accuracy
<50ms
Latency
77
Categories
// Pipeline Architecture
📥
Raw Ticket Text
Unstructured customer input
🔢
TF-IDF Vectorization
Term frequency × inverse document freq
🧠
Logistic Regression
Multiclass softmax classification
✅
Confidence-Based Routing
Auto-route or escalate to human review
Live Demo
// classify a ticket
Ticket Input
Quick examples
Classification Result
🎯
Enter a ticket and click Classify
to see the predicted department
Supported Classifications
// 77 total categories
Activate My Card
Age Limit
Apple Pay Or Google Pay
Atm Support
Automatic Top Up
Balance Not Updated After Bank Transfer
Balance Not Updated After Cheque Or Cash Deposit
Beneficiary Not Allowed
Cancel Transfer
Card About To Expire
Card Acceptance
Card Arrival
Card Delivery Estimate
Card Linking
Card Not Working
Card Payment Fee Charged
Card Payment Not Recognised
Card Payment Wrong Exchange Rate
Card Swallowed
Cash Withdrawal Charge
Cash Withdrawal Not Recognised
Change Pin
Compromised Card
Contactless Not Working
Country Support
Declined Card Payment
Declined Cash Withdrawal
Declined Transfer
Direct Debit Payment Not Recognised
Disposable Card Limits
Edit Personal Details
Exchange Charge
Exchange Rate
Exchange Via App
Extra Charge On Statement
Failed Transfer
Fiat Currency Support
Get Disposable Virtual Card
Get Physical Card
Getting Spare Card
Getting Virtual Card
Lost Or Stolen Card
Lost Or Stolen Phone
Order Physical Card
Passcode Forgotten
Pending Card Payment
Pending Cash Withdrawal
Pending Top Up
Pending Transfer
Pin Blocked
Receiving Money
Refund Not Showing Up
Request Refund
Reverted Card Payment
Supported Cards And Currencies
Terminate Account
Top Up By Bank Transfer Charge
Top Up By Card Charge
Top Up By Cash Or Cheque
Top Up Failed
Top Up Limits
Top Up Reverted
Topping Up By Card
Transaction Charged Twice
Transfer Fee Charged
Transfer Into Account
Transfer Not Received By Recipient
Transfer Timing
Unable To Verify Identity
Verify My Identity
Verify Source Of Funds
Verify Top Up
Virtual Card Not Working
Visa Or Mastercard
Why Verify Identity
Wrong Amount Of Cash Received
Wrong Exchange Rate For Cash Withdrawal
How It Works
// under the hood
01
TF-IDF Vectorization

Each ticket is transformed into a sparse vector. Words common across all tickets get low weight; domain-specific terms get amplified — giving the model strong signal on intent.

scikit-learn n-gram support stop-word filter
02
Multiclass Classification

Logistic Regression with a softmax output layer predicts probability across all departments simultaneously. Fast, regularized, and produces calibrated confidence scores.

LogisticRegression L2 regularization softmax
03
Confidence-Based Routing

Tickets above the confidence threshold are auto-routed instantly. Below threshold, tickets escalate to human review — preventing costly misclassification in production.

threshold = 0.75 auto-route human review