Best Grok prompts for Mathematicians

Given a time series dataset with 100,000 data points, each representing a daily stock price, use a combination of statistical methods and machine learning algorithms to identify anomalous data points that are more than 3 standard deviations away from the mean. First, apply a rolling window approach to calculate the mean and standard deviation of the data over a 30-day period. Then, use a One-Class SVM to classify data points as either normal or anomalous. Finally, visualize the results using a scatter plot, highlighting the anomalous data points in red.

Analyze the query performance of a Snowflake database using SQL queries and Python scripts. First, use the Snowflake Query Profile tool to collect data on query execution times, CPU usage, and memory usage. Then, apply statistical methods such as regression analysis and hypothesis testing to identify the most significant factors affecting query performance. Next, use Python to simulate different query optimization scenarios, such as rewriting queries or reordering joins, and evaluate their impact on performance. Finally, provide recommendations for optimizing query performance based on the analysis.

Given a dataset with 10 features and 1,000 samples, each representing a customer's demographic and transactional data, use a combination of statistical methods and machine learning algorithms to select the best predictive model for forecasting customer churn. First, apply feature selection techniques such as correlation analysis and mutual information to reduce the dimensionality of the data. Then, use cross-validation to evaluate the performance of different models, including logistic regression, decision trees, and random forests. Finally, compare the results and select the model with the highest precision and recall.

Evaluate the data quality of a large dataset containing customer information, including names, addresses, and phone numbers. First, use statistical methods such as summary statistics and data visualization to identify missing, duplicate, or erroneous data. Then, apply data cleaning techniques such as data normalization, handling outliers, and data imputation to correct errors and inconsistencies. Next, use data validation rules to check for data integrity and consistency. Finally, provide a report on the data quality issues found and the steps taken to clean and preprocess the data.