Spaces:
Sleeping
Sleeping
| title: TurnoverForecasting | |
| emoji: 📊 | |
| colorFrom: blue | |
| colorTo: red | |
| sdk: gradio | |
| sdk_version: 5.22.0 | |
| app_file: app.py | |
| pinned: false | |
| license: mit | |
| short_description: Forecasting SAP SE Revenue with AI | |
| # 📊 AI-Powered Turnover Forecasting for SAP SE | |
| ## 🚀 Project Overview | |
| This project delivers **AI-driven revenue forecasting** for **SAP SE** using a **univariate SARIMA model**. The focus is to demonstrate how reliable forecasts can be achieved with **minimal data** — only historical turnover — making this approach powerful for both large enterprises and **resource-constrained settings**. | |
| --- | |
| ## 📌 Why Univariate Forecasting? | |
| - 🔎 **Focus on one key variable — Revenue** | |
| - ✅ Ideal when limited data is available | |
| - 🧠 Easier to interpret and communicate results | |
| - 🚀 Fast to train, test, and deploy | |
| - 💡 Great for early-stage AI adoption and small business analytics | |
| --- | |
| ## 🏢 Why SAP SE? | |
| - SAP SE is a **global leader in enterprise software** | |
| - Accurate revenue forecasts support **strategic planning, risk management, and growth** | |
| - As a digital-first company, SAP is ideal for showcasing **AI integration in financial operations** | |
| --- | |
| ## 🛠️ Technical Approach | |
| - **SARIMA** model (Seasonal ARIMA) for time-series forecasting | |
| - Forecast horizon: **1 to 6 quarters** | |
| - Built-in **walk-forward validation** | |
| - **Gradio UI** for interactive forecasting | |
| - Visuals powered by **Plotly** | |
| --- | |
| ## 📊 Dataset | |
| - Source: [Top 12 German Companies Financial Data (Kaggle)](https://www.kaggle.com/datasets/heidarmirhajisadati/top-12-german-companies-financial-data) | |
| - Focused subset: **SAP SE revenue over time** | |
| - Realistic industry dataset for enterprise-level modeling | |
| --- | |
| ## 🎯 Features | |
| - Predict revenue trends with confidence intervals | |
| - Dynamic forecasting by adjusting horizon and confidence level | |
| - Interactive and mobile-friendly layout (single-column Gradio) | |
| - Insightful visual comparisons: Training, Validation, Test & Future Forecasts | |
| --- | |
| ## ⚙️ How to Run | |
| ```bash | |
| git clone https://github.com/Sharma-Pranav/Portfolio.git | |
| cd projects/TurnoverForecasting | |
| pip install -r requirements.txt | |
| python app.py | |
| --- | |
| ## **📌 Results** | |
| - **Accurate Accurate revenue forecasting for SAP SE for better financial planning. ** | |
| - **Optimized financial planning & business strategy insights.** | |
| - **Walk-Forward Validation ensures model reliability over time.**. | |
| ``` | |
| --- | |
| ## 🌐 Try It Live on Hugging Face | |
| Experience the project **without installing anything**! | |
| 🚀 Just head to the hosted interactive demo: | |
| 👉 **[Launch the Forecasting App](https://huggingface.co/spaces/PranavSharma/TurnoverForecasting)** | |
| [](https://huggingface.co/spaces/PranavSharma/TurnoverForecasting) | |
| --- | |
| ### 🔍 What You Can Do: | |
| - 📅 **Select Forecast Horizon** – Choose how many future quarters (1–6) to predict | |
| - 🎯 **Adjust Confidence Level** – See uncertainty intervals dynamically | |
| - 📈 **Visualize Forecasts** – Instantly view training vs. validation vs. future forecasts | |
| - 📲 **Use on Any Device** – Mobile-optimized for fast access anywhere | |
| --- | |
| 📌 **Developed by:** Pranav Sharma | |
| 📆 **Project Start Date:** February 2025 | |
| 📁 **Repository:** https://github.com/Sharma-Pranav/Portfolio/ | |