Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,52 @@
|
|
1 |
-
---
|
2 |
-
license: apache-2.0
|
3 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
---
|
4 |
+
# Revenue Assurance and Fraud Management (RAFM) with AI Assistance
|
5 |
+
|
6 |
+
## Project Overview
|
7 |
+
|
8 |
+
This project aims to deliver an RAFM prediction (if that particular telco transaction is fraudulent or not) with a AI model assistance with; <br>
|
9 |
+
(1) Balanced Random Forest,<br>
|
10 |
+
The model has trained on semi-synthetic telecom data to predict fraud cases and identify potential anomalies. The goal is to provide proactive revenue management and enhance revenue workflows.
|
11 |
+
|
12 |
+
## Data
|
13 |
+
![Revenue Assurance Data Structure](https://raw.githubusercontent.com/fenar/etc-ai-wrx/main/revenueassurance/data/rev_ass_data.png)<br>
|
14 |
+
|
15 |
+
## Results:
|
16 |
+
![Revenue Assurance Accuracy](https://raw.githubusercontent.com/fenar/etc-ai-wrx/main/revenueassurance/data/rev_ass_models_accuracy.png)<br>
|
17 |
+
|
18 |
+
## Steps to Test
|
19 |
+
(A) Potential Fraud Test: <br>
|
20 |
+
```
|
21 |
+
curl -X POST -H "Content-Type: application/json" -d '{
|
22 |
+
"Call_Duration": 300,
|
23 |
+
"Data_Usage": 10000,
|
24 |
+
"Sms_Count": 50,
|
25 |
+
"Roaming_Indicator": 1,
|
26 |
+
"MobileWallet_Use": 1,
|
27 |
+
"Plan_Type_prepaid": 1,
|
28 |
+
"Plan_Type_postpaid": 0,
|
29 |
+
"Cost": 500,
|
30 |
+
"Cellular_Location_Distance": 100,
|
31 |
+
"Personal_Pin_Used": 0,
|
32 |
+
"Avg_Call_Duration": 50,
|
33 |
+
"Avg_Data_Usage": 8000
|
34 |
+
}' http://localhost:5000/predict
|
35 |
+
```
|
36 |
+
(B) Potential Non-Fraud Test: <br>
|
37 |
+
```
|
38 |
+
curl -X POST -H "Content-Type: application/json" -d '{
|
39 |
+
"Call_Duration": 10,
|
40 |
+
"Data_Usage": 300,
|
41 |
+
"Sms_Count": 5,
|
42 |
+
"Roaming_Indicator": 0,
|
43 |
+
"MobileWallet_Use": 1,
|
44 |
+
"Plan_Type_prepaid": 1,
|
45 |
+
"Plan_Type_postpaid": 0,
|
46 |
+
"Cost": 50,
|
47 |
+
"Cellular_Location_Distance": 3,
|
48 |
+
"Personal_Pin_Used": 1,
|
49 |
+
"Avg_Call_Duration": 12,
|
50 |
+
"Avg_Data_Usage": 350
|
51 |
+
}' http://localhost:5000/predict
|
52 |
+
```
|