ifiecas commited on
Commit
d740257
·
verified ·
1 Parent(s): 306fcc4

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +5 -5
app.py CHANGED
@@ -320,18 +320,18 @@ with tab2:
320
  </style>
321
  """, unsafe_allow_html=True)
322
 
323
- # Use completely clean approach with no custom HTML/CSS
324
- st.header("About the Loan Approval System")
325
  st.write("Our AI-powered system evaluates loan applications using machine learning and industry-standard criteria to analyze your financial information, credit history, and loan requirements.")
326
 
327
- st.header("About the ML Model")
328
  st.write("""The machine learning model used here is a Decision Tree, which was the best performing model among KNN,
329
  Random Forest, Logistic Regression, and Support Vector Machine models tested.
330
 
331
  The Decision Tree model was further refined using Cost Complexity Pruning (CCP) to find the optimal
332
  alpha value for pruning, which helps prevent overfitting while maintaining high accuracy.""")
333
 
334
- st.subheader("Model Performance Metrics:")
335
  st.markdown("""
336
  - Accuracy: 0.8361
337
  - Precision: 0.8077
@@ -343,7 +343,7 @@ with tab2:
343
 
344
  st.write("Enjoyed doing this and learned a lot! 😊")
345
 
346
- st.header("Behind the Build")
347
  st.markdown("[Ivy Fiecas-Borjal](https://ifiecas.com/)")
348
  st.write("Inspired by an assessment in BCO6008 Predictive Analytics class in Victoria University (Melbourne) with Dr. Omid Ameri Sianaki")
349
 
 
320
  </style>
321
  """, unsafe_allow_html=True)
322
 
323
+ # Use regular paragraphs with bold text for titles
324
+ st.markdown("**About the Loan Approval System**")
325
  st.write("Our AI-powered system evaluates loan applications using machine learning and industry-standard criteria to analyze your financial information, credit history, and loan requirements.")
326
 
327
+ st.markdown("**About the ML Model**")
328
  st.write("""The machine learning model used here is a Decision Tree, which was the best performing model among KNN,
329
  Random Forest, Logistic Regression, and Support Vector Machine models tested.
330
 
331
  The Decision Tree model was further refined using Cost Complexity Pruning (CCP) to find the optimal
332
  alpha value for pruning, which helps prevent overfitting while maintaining high accuracy.""")
333
 
334
+ st.markdown("**Model Performance Metrics:**")
335
  st.markdown("""
336
  - Accuracy: 0.8361
337
  - Precision: 0.8077
 
343
 
344
  st.write("Enjoyed doing this and learned a lot! 😊")
345
 
346
+ st.markdown("**Behind the Build**")
347
  st.markdown("[Ivy Fiecas-Borjal](https://ifiecas.com/)")
348
  st.write("Inspired by an assessment in BCO6008 Predictive Analytics class in Victoria University (Melbourne) with Dr. Omid Ameri Sianaki")
349