---
title: Workforce Optimization AI
emoji: 📞
colorFrom: blue
colorTo: green
sdk: streamlit
sdk_version: 1.56.0
app_file: app.py
pinned: false
---

# 📞 Workforce Optimization AI / İş Gücü Optimizasyonu

This project is an AI-driven decision support system designed to optimize staffing levels based on historical call/demand data. It uses Long Short-Term Memory (LSTM) networks to predict future demand and suggests actionable staffing strategies.

Bu proje, geçmiş çağrı/talep verilerine dayanarak personel seviyelerini optimize etmek için tasarlanmış yapay zeka destekli bir karar destek sistemidir. Gelecekteki talebi tahmin etmek için LSTM ağlarını kullanır ve uygulanabilir personel stratejileri önerir.

## 🚀 Features / Özellikler

- **AI Demand Forecasting:** Predicts future call volumes using deep learning.
- **Strategic Recommendations:** Automatically identifies "High Intensity" (Risk) and "Saving Area" (Opportunity) periods.
- **Cost Optimization:** Helps managers balance service quality and labor costs.
- **Interactive Visualization:** Dynamic charts showing demand vs. staff capacity.

## 🛠️ Tech Stack / Teknolojiler

- **Python** (Core Logic)
- **TensorFlow/Keras** (LSTM Model)
- **Streamlit** (Web Interface)
- **Plotly** (Interactive Graphics)
- **Scikit-Learn** (Data Scaling)

## 📖 How to Use / Nasıl Kullanılır?

1. **Upload Data:** Upload a CSV file containing a column named `calls`.
2. **Set Parameters:** Adjust hourly wage and staff capacity per hour from the sidebar.
3. **Analyze:** - View the **Decision Logic** to understand AI suggestions.
   - Check the **Strategic Recommendations** for peak and low-demand periods.
   - Download the **Detailed Schedule** for operational planning.

---

### 🧠 Strategic Logic / Stratejik Mantık

- **High Intensity (🔥):** When predicted demand exceeds capacity. Action: Increase staff to prevent customer loss.
- **Saving Area (💰):** When demand is significantly lower than capacity. Action: Reduce staff or plan breaks to minimize labor waste.

**Note:** Each "Slot" in the analysis represents a sequential row from your uploaded data (e.g., Slot 0 = 08:00 AM, Slot 1 = 09:00 AM).
---