Case Study: Optimising Pricing Strategy

Client

A global long-term accommodation rental company.

Problem

The client needed to develop an optimal pricing strategy to maximise annual revenue. This required accurately forecasting demand and availability while considering a vast array of client data. The complexity of predicting these variables and finding the balance between occupancy and pricing posed a significant challenge, and the stakes were high as the client’s margins were on the line.

How We Helped

We developed a predictive machine learning model of customer behaviour using the client’s data. Our model analysed historical data to accurately forecast demand and availability. With these insights, we implemented an end-to-end optimal pricing solution designed to maximise annual revenue. Our solution drove the strategy of finding the sweet spot between taking the risk of leaving a flat vacant for a short period to rent it at a higher price later. This approach ensured that overall revenue was maximised over 12 months. The solution could continuously adjust prices based on real-time data, ensuring the strategy remained effective under varying market conditions.

Impact

Our end-to-end solution enabled the client to significantly boost their annual revenue. By accurately forecasting demand and adjusting prices dynamically, the client could optimise occupancy rates and revenue streams. The optimisation strategy ensured that flats were rented at the most profitable times, balancing the risk of vacancy with the potential for higher rental income.