Performance Analysis of Accurate Credit Scoring of Individuals with Limited Financial Histories
Implementation plan:
Step 1: Initially, we collect the data from the “Synthetic Credit Score of Thin File Consumers” Dataset .
Step 2: Then, we pre-process the collected Data using Min-Max normalization method.
Step 3: Next, we implement optimal Feature selection process such as population update, diversity preservation, and fast non-dominated sorting using Non-dominated Sorting Genetic Algorithm (NSGA-II) .
Step 4: Next, we implement Mitigation Strategies to prevent overfitting using multi-layer perceptron Artificial Neural Network (MLP-ANN) Architecture.
step 5:Next , we Train the model using Bayesian Hyper-parameters optimized XGBoost (BH-OXGB) method.
step 6: Next, we classify the data using fuzzy rule-based classifiers- Quantum Particle Swarm Optimization (FRBC-QPSO) method.
Step 7:Finally, we plot performance for the following metrics:
7.1 Number of iterations vs. Accuracy(%)
7.2 Number of iterations vs. Precision(%)
7.3 Number of iterations vs. Recall(%)
7.4 Number of iterations vs. F1 Score(%)
7.5 Number of iterations Vs. AUC-ROC Curve
Software Requirement:
1. Development Tool: Python – 3.11.4
2. Operating System: Windows 11 (64-bit)
Note:
1) If the above plan does not satisfy your requirement, please provide the processing details, like the above step-by-step.
2) Please note that this implementation plan does not include any further steps after it is put into implementation.
3) If the above plan satisfies your requirement please confirm with us.
4) We develop simulation based projects only, not in real time
We perform the EXISTING Approach based on the Reference 4 Title:-Ensemble of deep sequential models for credit card fraud detection
