PD03 commited on
Commit
a637bc5
Β·
verified Β·
1 Parent(s): 2aa04e8

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +45 -13
README.md CHANGED
@@ -1,19 +1,51 @@
1
  ---
2
- title: RICA AIRevenueIntelligenceAgent
3
- emoji: πŸš€
4
- colorFrom: red
5
- colorTo: red
6
- sdk: docker
7
- app_port: 8501
8
- tags:
9
- - streamlit
10
  pinned: false
11
- short_description: Streamlit template space
 
12
  ---
13
 
14
- # Welcome to Streamlit!
15
 
16
- Edit `/src/streamlit_app.py` to customize this app to your heart's desire. :heart:
17
 
18
- If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
19
- forums](https://discuss.streamlit.io).
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ title: RICA - AI Revenue Intelligence Agent
3
+ emoji: πŸ€–
4
+ colorFrom: blue
5
+ colorTo: purple
6
+ sdk: streamlit
7
+ sdk_version: 1.28.0
8
+ app_file: app.py
 
9
  pinned: false
10
+ license: mit
11
+ python_version: 3.9
12
  ---
13
 
14
+ # πŸ€– RICA - Revenue Intelligence & Customer Analytics Agent
15
 
16
+ Advanced AI agent for autonomous business intelligence using SAP data and machine learning.
17
 
18
+ ## Features
19
+
20
+ - 🧠 **AI-Powered Churn Prediction**: Machine learning models predict customer churn risk
21
+ - πŸ“Š **Real-time Data Analysis**: Direct analysis of SAP data structures
22
+ - 🌐 **Market Intelligence**: External data integration and competitive insights
23
+ - πŸ€– **Autonomous Agent**: LLM-powered decision making and recommendations
24
+ - πŸ“ˆ **Business Impact**: Actionable insights for revenue optimization
25
+
26
+ ## Technology Stack
27
+
28
+ - **Agent Framework**: smolagents with OpenAI GPT
29
+ - **ML Models**: Scikit-learn with automated training
30
+ - **Data Processing**: DuckDB for high-performance analytics
31
+ - **Real SAP Data**: SAP/SALT dataset from Hugging Face Hub
32
+ - **UI**: Streamlit for interactive experience
33
+
34
+ ## Usage
35
+
36
+ 1. Enter your OpenAI API key in the sidebar
37
+ 2. Select analysis type (Comprehensive Review, Churn Analysis, etc.)
38
+ 3. Click "Run Analysis" to execute AI-powered insights
39
+ 4. Review recommendations and take action
40
+
41
+ ## Model Training
42
+
43
+ The churn prediction model is automatically trained on first use using real SAP customer and sales data. Training typically takes 1-2 minutes and creates a persistent model for future predictions.
44
+
45
+ ## Data Sources
46
+
47
+ - **Customer Data**: I_Customer from SAP/SALT dataset
48
+ - **Sales Data**: I_SalesDocument and I_SalesDocumentItem
49
+ - **External Data**: Industry news and competitive intelligence
50
+
51
+ Built with ❀️ for enterprise AI and business intelligence.