Best Perplexity prompts for Credit Analysts

Write a Python script using scikit-learn to optimize a logistic regression model for predicting credit risk, incorporating L1 and L2 regularization, and compare the results to a baseline model without regularization, using a dataset of 10,000 samples with 20 features, and provide a statistical summary of the results, including coefficients, p-values, and ROC-AUC scores.

Design an ETL pipeline using SQL and Python to extract credit data from a Snowflake database, transform it into a suitable format for analysis, and load it into a Tableau dashboard for visualization, including handling missing values, data normalization, and data quality checks, and provide a detailed description of the pipeline architecture and data flow.

Develop a validation framework for a credit scoring model using Python and R, including backtesting, walk-forward optimization, and performance metrics such as accuracy, precision, and recall, and provide a concise report on the model's strengths and weaknesses, including recommendations for improvement, using a dataset of 5,000 samples with 15 features.

Create a data cleaning script using Python and SQL to identify and correct errors in a credit dataset, including handling missing values, outliers, and inconsistencies, and provide a detailed data quality report, including statistics on data completeness, accuracy, and consistency, and recommendations for data quality improvement, using a dataset of 20,000 samples with 30 features.