Meet Sarah. Sarah owns a city property that she is looking to rent on a short-term rental website. Sarah is determining how to set the right price for the apartment. She knows that pricing is a delicate balancing act. If she prices it too high, potential guests may look elsewhere. On the other hand, if her price is too low, she might not make the profit she hoped for. Sarah begins her journey by researching her competition. She checks similar listings in her area, looking at other hosts' prices and reviews. She notices that some places are more expensive sometimes and cheaper other times. Sarah realizes that the demand might varies throughout the year.She understands that setting dynamic prices based on seasonal demand could be a good strategy.

Sarah learned about Airbnb's dynamic pricing algorithm, which takes into account various factors such as demand, local events, and historical data. The algorithm suggests price adjustments that can help her maximize her earnings. Sarah sees not only does the model provides her with its predicted prices for her place, but it also includes a measure of uncertainty in those predictions. This uncertainty quantifies the AI model's confidence in its forecasts.

You are asked to play the role of Sarah. After a few months away from the hosting a short-term rental market you are re-entering again trying to maximize your profit from your listing. Current market data: You are asked to set prices for a month. You will get a table of information about your neighbours prices at the moment, their past reviews, their number of bedrooms and bathrooms and whether they have been already booked at the moment for those dates. Past Market data: You will also receive the price of the neighbourhood listing and your listing for the last year in the same month. These two years' demands are similar. This game will be played for 1 round.