IFRS 9 Model Development

Data Foundation & Implementation Checklist - Build robust, auditable, and compliant Expected Credit Loss (ECL) models

Implementation Progress

0%

Phase 1: Foundation Setup

Page 1 Tickmark

Upload Accounting Policy Documents

📄

Drag & drop files or click to upload

Supported: PDF, DOC, DOCX, XLS, XLSX, CSV

Page 1 Tickmark

Upload Governance Framework Documents

📋

Drag & drop files or click to upload

Supported: PDF, DOC, DOCX, XLS, XLSX, CSV

Page 1 Tickmark

Upload Portfolio Segmentation Data

📊

Drag & drop files or click to upload

Supported: CSV, XLS, XLSX

Page 2

Data Gathering

📁

Upload Main Loan Portfolio Data

Click to upload or drag and drop your data files here

Supported: .csv, .xlsx, .xls

Data Requirements

Loan & Customer Data Fields

Loan No
Relationship No
Type
Term
Collateral
Original Amount
Outstanding Balance
Delinquency
Overdue
Tenure
Product Date
Payments Made
Bureau Score
Status
A Score
Date of Application
Application Status
Salary
Occupation
Address
B Score
Date of Score
Score
Portfolio Type
Acquisition Price
Disposal Price
Date of Sell
Asset Sell Cost
Appraised Value
Date of Repossession
Legal Charges
Recoveries
Date of Recoveries
Customer ID
Credit Limit
Utilization Rate
Payment History
Days Past Due
Interest Rate
Maturity Date
Origination Channel
Branch Code
Product Code
Risk Rating
Industry Code
Region
Customer Segment
Vintage
Cohort

Macro Economic Data

GDP
Unemployment Rate
Consumer Price Index
BSP Rate
FX Rate
PDEX Rate
Inflation Rate
Interest Rate Trend
HPI (House Price Index)
Stock Market Index
Oil Price
Exchange Rate Volatility

RUN Data Clean Up

Run each cleanup function individually. Results will display below each function.

📊 Handling missing values, duplicates, type conversions, filtering, merging, reshaping Pending
🔄 Replace NaNs, normalize values, vectorized operations for speed Pending
🧹 Clean names, remove empty, encode categorical Pending
⚡ Parallelized version for large datasets Pending
📝 Text transformations, clustering, reconciliation Pending
📈 Normalization, scaling, encoding categorical variables, imputation Pending

💡 Data Cleanup Recommendations

Dashboard on Data Clean Up

Total Records Processed
0
Missing Values Handled
0
Duplicates Removed
0
Data Quality Score
0%

📊 Data Quality Trends Over Time

📈 Cleanup Functions Performance

🎯 Data Distribution Before & After Cleanup