Prompt lesson · 23 prompts
AI for Predictive Analytics prompts for Data Scientists
23 ready-to-use prompts from our AI for Data Scientists course. Copy one, fill in the {{placeholders}}, and paste it into ChatGPT, Claude, Gemini or any other AI.
Data Preprocessing Guidance
Use this when you need to clean, transform, and prepare datasets for analysis or machine learning.
Role You are a data preprocessing expert. Your goal is to provide clear, practical guidance on cleaning, transforming, and normalizing data to ensure high-quality inputs for analysis and modeling.
Context you provide
- {{dataset_description}}: Describe your dataset, including number of records, features, and types (numeric, categorical, text).
- {{preprocessing_goal}}: Specify what you need help with (e.g., missing values, outliers, scaling, encoding, text preprocessing).
- {{specific_features}}: List the features you are concerned about.
- {{constraints}}: Mention any constraints like data size, software environment, or reproducibility needs.
Instructions
- If any context is missing, ask for it before proceeding.
- Based on the dataset description, identify potential data quality issues (e.g., missing values, outliers, inconsistent formats).
- Provide step-by-step methods for handling missing values (e.g., imputation, deletion) and outliers (e.g., IQR, z-score).
- Explain how to scale numerical features (e.g., standardization, min-max scaling) and when to use each.
- Recommend approaches for encoding categorical variables (e.g., one-hot, label) with trade-offs.
- For text data, outline preprocessing steps like tokenization, stemming, and stop-word removal.
- Suggest tools or libraries (e.g., pandas, scikit-learn) and emphasize reproducibility.
Output format Provide a structured guide with sections: Data Quality Check, Handling Missing Values, Outlier Treatment, Scaling, Categorical Encoding, Text Preprocessing, and Reproducibility Tips. Use bullet points and code snippets where helpful. Tone should be instructive and accessible.
Guardrails
- Do not assume specific data values; base recommendations on the description.
- Flag any assumptions about the data distribution or domain.
- Stay within preprocessing scope; do not dive into modeling.
Example Dataset: 10,000 records with features like age, income (numeric), and product category (categorical); Goal: clean and prepare for regression; Specific features: income and product category; Constraints: use Python.
Open this prompt Analysis · Beginner
Feature Selection for Modeling
Use this when you need to identify the most relevant features for predictive modeling to improve performance and reduce overfitting.
Role You are a machine learning expert specializing in feature selection. Your goal is to help identify the most predictive features for a given outcome, improving model performance and interpretability.
Context you provide
- {{dataset_description}}: Describe your dataset, including number of records and features.
- {{outcome_variable}}: Specify the target variable you want to predict.
- {{feature_concerns}}: Mention any known issues like multicollinearity, high dimensionality, or irrelevant features.
- {{model_type}}: If you have a preferred model (e.g., regression, tree-based), mention it.
- {{constraints}}: Note any constraints like computational resources or need for interpretability.
Instructions
- If any context is missing, ask for it before proceeding.
- Based on the dataset description, suggest appropriate feature selection methods (e.g., filter, wrapper, embedded).
- Explain how to handle multicollinearity (e.g., VIF, correlation analysis).
- Provide a step-by-step approach for ranking features by importance (e.g., using mutual information, feature importance from models).
- Discuss regularization techniques (e.g., Lasso, Ridge) and how they aid feature selection.
- Recommend a subset of features that balances predictive performance and overfitting.
- Explain how to interpret the impact of each feature on the model's predictions.
Output format Provide a structured response with sections: Recommended Methods, Step-by-Step Process, Feature Ranking, Regularization, and Interpretation. Use bullet points and tables. Tone should be technical and instructive.
Guardrails
- Do not assume specific data values; base recommendations on the description.
- Flag any assumptions about the data distribution or model type.
- Stay within feature selection scope; do not dive into full model building.
Example Dataset: 5,000 records with 200 features; Outcome: customer churn (binary); Concerns: high multicollinearity; Model: logistic regression; Constraints: need interpretable features.
Open this prompt Analysis · Intermediate
Select the Right ML Model
Use this when you need to choose the most suitable machine learning model for your dataset and prediction task.
Open this prompt Decisions · Intermediate
Hyperparameter Tuning Guide
Use this when you need to optimize machine learning model performance through effective hyperparameter selection.
Open this prompt Learning · Intermediate
Prepare Data for Model Training
Use this when you need to preprocess and clean historical data to train a machine learning model effectively.
Open this prompt Analysis · Intermediate
Model Evaluation Metrics Guide
Use this when you need to evaluate the performance of predictive models using appropriate metrics.
Open this prompt Analysis · Intermediate
Model Deployment Playbook
Use this when you need to deploy trained machine learning models into production for real-time predictions.
Open this prompt Planning · Advanced
Time Series Forecasting Methodology
Use this when you need to develop or improve time series forecasting models, including data preprocessing, feature engineering, and model selection.
Open this prompt Research · Advanced
Detect Anomalies in Data
Use this when you need to identify unusual patterns or outliers in your dataset to support predictive analytics and monitoring.
Open this prompt Analysis · Intermediate
Customer Segmentation Analysis
Use this when you need to segment customers into distinct groups for targeted marketing, personalization, or strategic planning.
Open this prompt Analysis · Intermediate
Predict Customer Churn
Use this when you need to analyze customer data to predict churn and develop retention strategies.
Open this prompt Analysis · Intermediate
Fraud Detection Model Design
Use this when you need to build or improve a fraud detection system based on historical transaction data.
Open this prompt Analysis · Advanced
Demand Forecasting Strategy
Use this when you need to forecast product or service demand using historical data and external factors.
Open this prompt Analysis · Intermediate
Assess and Predict Risks
Use this when you need to analyze potential risks for an event or scenario and develop mitigation strategies.
Open this prompt Analysis · Advanced
Forecast Sales with Historical Data
Use this when you need to predict future sales volumes based on historical data to support inventory and resource planning.
Open this prompt Analysis · Intermediate
Sales Forecasting Analysis
Use this when you need to analyze historical sales data and generate forecasts to inform resource allocation and strategic planning.
Open this prompt Analysis · Intermediate
Market Trend Analysis Framework
Use this when you need to analyze historical market data and external factors to predict future trends for strategic decisions.
Open this prompt Analysis · Intermediate
Sentiment Analysis Insights
Use this when you need to analyze textual data (reviews, social media, surveys) to understand customer sentiment and derive actionable insights.
Open this prompt Analysis · Intermediate
Build Personalized Recommendation Systems
Use this when you need to design or improve a recommendation system that tailors suggestions to individual users.
Open this prompt Creating · Advanced
Credit Scoring Model Development
Use this when you need to develop or analyze credit scoring models, including risk assessment and regulatory compliance.
Open this prompt Analysis · Advanced
Supply Chain Optimization Analysis
Use this when you need to analyze supply chain data to improve efficiency, reduce costs, and optimize inventory and logistics.
Open this prompt Analysis · Intermediate
Stock Market Prediction Guidance
Use this when you need guidance on developing AI models to analyze historical stock data and predict future price movements.
Open this prompt Research · Advanced
Assess Credit Risk
Use this when you need to analyze borrower data to predict lending risk and make informed credit decisions.
Open this prompt Analysis · Advanced