---
title: AI Ticket Classifier
emoji: 🧠
colorFrom: indigo
colorTo: purple
sdk: streamlit
sdk_version: 1.41.1
app_file: app.py
pinned: false
---

# 🧠 AI Ticket Classifier

An AI-powered support ticket classification system that groups tickets by intent and generates automated responses using NLP techniques.

---

## 📌 Problem Statement

Organizations receive hundreds of support tickets daily. Manually categorizing and routing each ticket is slow and error-prone. This system uses **TF-IDF**, **Cosine Similarity**, and **Keyword Matching** to instantly classify, group, and respond to tickets.

## 📋 Sample Tickets

| # | Ticket | Classified As |
|---|--------|---------------|
| 1 | "I forgot my password, how to reset it?" | 🔐 Password / Authentication |
| 2 | "I can't log in, as password is incorrect" | 🔐 Password / Authentication |
| 3 | "How to see leave balance?" | 📊 HR / Leave Management |

**Result:** Tickets 1 & 2 → grouped together (password-related), Ticket 3 → separate group (HR-related).

---

## 🛠️ Technologies Used

| Technology | Purpose |
|------------|---------|
| Python 3 | Core language |
| Streamlit | Interactive web UI |
| scikit-learn | TF-IDF vectorization, cosine similarity |
| pandas / numpy | Data handling |

---

## 📂 File Structure

```
AI Design/
├── ticket_classifier.py    → Main Streamlit app (NLP engine + UI)
├── requirements.txt        → Python dependencies
├── REPORT.md               → Detailed project report
└── README.md               → This file
```

---

## 🚀 How to Run

### Prerequisites
- Python 3.8 or later — [Download](https://python.org)

### Steps

```bash
# 1. Navigate to the project folder
cd "c:\Users\sakthi\Documents\AI Design"

# 2. Install dependencies
pip install -r requirements.txt

# 3. Run the app
streamlit run ticket_classifier.py

# 4. Browser opens automatically at http://localhost:8501
```

---

## ⚙️ How It Works

```
User enters ticket
       │
       ▼
Text Preprocessing (lowercase, remove punctuation, stop words)
       │
       ▼
Keyword Matching (compare against category keyword lists)
       │
       ▼
Scoring & Classification (highest score → category + confidence)
       │
       ▼
Display Result (category badge, confidence bar, auto-response)
       │
       ▼
Grouping (add to category group, update similarity matrix)
```

### NLP Techniques
- **Tokenization** — splits text into individual words
- **Stop Word Removal** — removes common words (a, the, is, are)
- **TF-IDF** — scores words by importance (frequent in one ticket, rare across all)
- **Cosine Similarity** — measures how similar two tickets are (0 = different, 1 = identical)
- **Keyword Matching** — matches ticket text against predefined category keywords

---

## 📊 Supported Categories

| Category | Example Keywords |
|----------|-----------------|
| 🔐 Password / Auth | password, reset, forgot, login, credentials |
| 📊 HR / Leave | leave, balance, salary, work from home, payroll |
| 💻 IT / Hardware | laptop, slow, crash, printer, software |
| 🌐 Network | vpn, wifi, internet, connection, firewall |
| 🔑 Access / Permissions | access, permission, shared drive, repository |
| ❓ General | (fallback for unmatched tickets) |

---

## 📈 Features

- ✅ Instant ticket classification with confidence scores
- ✅ Automated responses from knowledge base
- ✅ Visual ticket grouping by category
- ✅ Interactive similarity matrix heatmap
- ✅ 3 pre-loaded example tickets
- ✅ Premium dark-mode UI
- ✅ No external API or cloud services needed