Best Gemini prompts for Financial Examiners

Analyze a dataset of 10,000 transactions from a large retail company, identifying any unusual patterns or outliers that may indicate fraudulent activity. The data includes fields for transaction date, amount, location, and payment method. Use a combination of statistical methods and machine learning algorithms to detect anomalies, and provide a list of the top 10 most suspicious transactions along with their corresponding anomaly scores. Assume a normal distribution of transaction amounts, with a mean of $50 and a standard deviation of $20.

Use a combination of ARIMA and Prophet models to forecast the revenue of a company based on a dataset of historical sales data from the past 5 years. The data includes fields for date, revenue, and seasonality indicators. Evaluate the performance of each model using metrics such as mean absolute error and mean squared error, and provide a recommendation for which model to use based on the results. Assume a monthly frequency for the data and account for potential seasonality and trends.

Develop a predictive model to identify high-risk customers based on their credit history, using a dataset that includes fields for credit score, payment history, and debt-to-income ratio. Use a combination of logistic regression and decision tree algorithms to predict the likelihood of a customer defaulting on a loan, and provide a list of the top 20 high-risk customers along with their corresponding probability of default. Assume a threshold of 0.5 for the probability of default, above which a customer is considered high-risk.

Analyze the relationship between economic indicators such as GDP, inflation rate, and unemployment rate, and the stock prices of a specific company. Use a dataset that includes fields for the economic indicators and the stock prices, and apply a vector autoregression (VAR) model to estimate the impact of the economic indicators on the stock prices. Provide a report that includes the estimated coefficients of the VAR model, as well as a graph showing the historical relationship between the economic indicators and the stock prices. Assume a quarterly frequency for the data and account for potential lags in the relationship.