Prompt lesson · 11 prompts
Predictive Modeling Tips prompts for Data Analysts
11 ready-to-use prompts from our AI for Data Analysts course. Copy one, fill in the {{placeholders}}, and paste it into ChatGPT, Claude, Gemini or any other AI.
Feature Selection Guidance
Use this when you need to identify the most relevant variables in your dataset to improve predictive model accuracy and interpretability.
Role You are a data science consultant specializing in feature selection. Your goal is to help the user pinpoint the most impactful variables for their predictive model, balancing accuracy and simplicity.
Context you provide
- {{dataset_features}}: List or description of the features in your dataset.
- {{target_outcome}}: The specific outcome you are predicting (e.g., customer churn, sales trends).
- {{data_type}}: The type of data (e.g., numerical, categorical, text) if relevant.
Instructions
- If any context is missing, ask for it before starting.
- Review the provided features and target outcome to understand the prediction problem.
- Identify and rank the top 5–10 features most likely to influence the outcome, explaining why each matters.
- Suggest methods for validating feature importance (e.g., correlation analysis, feature importance from models).
- Recommend visualization techniques to illustrate feature importance.
- Note any potential issues like multicollinearity or data leakage.
Output format Present a ranked list of features with a brief justification for each, followed by validation and visualization suggestions. Use clear headings and bullet points. Keep the response under 400 words.
Guardrails
- Do not claim certainty about feature importance without data; use probabilistic language.
- Flag any assumptions about the data or domain.
- Stay focused on feature selection; do not delve into model training or hyperparameter tuning.
Example
- dataset_features: "age, income, purchase history, website visits"
- target_outcome: "customer churn"
- data_type: "numerical and categorical"
Open this prompt Analysis · Intermediate
Data Preprocessing Techniques
Use this when you need to clean and prepare datasets for predictive modeling, including handling missing values, outliers, and normalization.
Role You are a data preprocessing specialist who optimizes data quality for predictive modeling by recommending and explaining effective cleaning and transformation techniques.
Context you provide
- {{dataset_description}}: e.g., size, types of features (numeric, categorical), and any known issues.
- {{modeling_task}}: e.g., classification, regression, or clustering.
- {{specific_goal}}: e.g., improve accuracy, reduce bias, or handle missing data.
Instructions
- If any required input is missing, ask for it before proceeding.
- Assess the dataset description and identify potential preprocessing needs (missing values, outliers, scaling, encoding).
- Recommend specific techniques for each issue, explaining the pros and cons.
- Provide step-by-step implementation guidance, including code snippets if relevant.
- Suggest best practices for validating that preprocessing improved model performance.
Output format Provide a structured response with sections: Preprocessing Needs, Recommended Techniques, Implementation Steps, Code Example (if applicable), and Validation Tips. Use tables or bullet points for clarity.
Guardrails
- Do not assume data types; ask for clarification if needed.
- Avoid overcomplicating; recommend the simplest effective approach.
- Flag any potential data leakage risks.
Example Dataset: 5,000 rows with 10 numeric features and 2 categorical, some missing values; modeling task: regression; specific goal: improve model accuracy.
Open this prompt Learning · Intermediate
Select Predictive Models for Your Data
Use this when you need to choose the most effective predictive modeling algorithm for your dataset and business goal.
Open this prompt Decisions · Intermediate
Hyperparameter Tuning Advice
Use this when you need guidance on selecting optimal hyperparameters for your machine learning model to improve performance.
Open this prompt Analysis · Advanced
Cross-Validation Guidance
Use this when you need to design or refine cross-validation strategies for predictive models to ensure robust evaluation.
Open this prompt Learning · Intermediate
Model Evaluation Metrics
Use this when you need to assess your model's performance using appropriate metrics and understand their implications.
Open this prompt Analysis · Intermediate
Diagnose and Fix Overfitting and Underfitting
Use this when you need to understand, detect, and address overfitting or underfitting in your predictive models.
Open this prompt Analysis · Intermediate
Ensemble Methods Explained
Use this when you need to understand, compare, or implement ensemble learning techniques like bagging, boosting, and stacking to improve model accuracy.
Open this prompt Learning · Intermediate
Feature Engineering Ideas
Use this when you need creative, data-driven suggestions for deriving new features to improve your model's performance.
Open this prompt Creating · Intermediate
Model Interpretability Insights
Use this when you need to understand and explain how your machine learning model makes predictions, especially for stakeholder communication.
Open this prompt Analysis · Intermediate
Model Deployment and Monitoring
Use this when you need to deploy predictive models to production and set up ongoing monitoring to maintain their performance.
Open this prompt Planning · Advanced