Best Gemini prompts for Meeting, Convention, and Event Planners

Given a dataset of 500 attendees, 20 speakers, and 15 breakout sessions, with constraints such as room capacity, speaker availability, and attendee preferences, generate an optimized event schedule that minimizes conflicts and maximizes attendee engagement, taking into account the following constraints: each speaker can only present once, each attendee can only attend one session per time slot, and each room can only host one session per time slot. Use a genetic algorithm to evolve the schedule over 100 iterations, with a population size of 50 and a mutation rate of 0.01. Output the optimized schedule in a CSV format, including the session title, speaker name, room number, and time slot.

Using a dataset of historical event attendance numbers, weather data, and economic indicators, train a machine learning model to predict the attendance numbers for an upcoming event, taking into account the following features: day of the week, month, temperature, precipitation, GDP growth rate, and unemployment rate. Use a random forest regressor with 100 trees, a maximum depth of 5, and a minimum sample split of 2. Output the predicted attendance numbers in a JSON format, including the predicted value, confidence interval, and feature importance scores.

Given a dataset of 10 rooms, each with its own capacity, layout, and amenities, and a dataset of 50 attendees, each with their own preferences and requirements, generate an assignment of attendees to rooms that maximizes attendee satisfaction and minimizes room conflicts, taking into account the following constraints: each attendee can only be assigned to one room, each room can only be assigned to one group of attendees, and each group of attendees must be assigned to a room that meets their requirements. Use a constraint programming approach to solve the assignment problem, with a objective function that maximizes attendee satisfaction and a constraint satisfaction threshold of 0.9. Output the assignment in a CSV format, including the attendee name, room number, and satisfaction score.

Using a dataset of historical event expenses, revenue, and attendance numbers, generate a forecast of the event budget for an upcoming event, taking into account the following factors: venue rental fees, catering costs, audiovisual equipment rental, speaker fees, and marketing expenses. Use a seasonal ARIMA model to forecast the expenses and revenue, with a seasonal period of 12 months and a confidence interval of 95%. Output the forecasted budget in a JSON format, including the predicted expenses, revenue, and profit, as well as the confidence interval and seasonal decomposition.