We explored our client’s new drive-through data to complete an analysis of each stage of the ordering process. The total service time of each transaction was narrowed down to four categories:
- Order Time: The number of seconds from the order beginning to when the order is initially stored in the database.
- Order End to Cash Begin: The number of seconds from the order stored into the database to when the order recall button is pressed for the transaction
- Cash Time: The number of seconds from when the order recall button is pressed for the transaction to when payment is received.
- Cash End to Present End: The number of seconds from when the payment is received until customer is served.
Our analysis revealed how times in the above categories differed for other ordering methods, including using the mobile app to order, using the app only for coupons, or walking into the restaurant to order.
As a result, our team of data scientists used Monte Carlo simulations, statistical analyses, and big data technologies alongside SMEs to develop a comprehensive solution that not only provided insight into current timings of different ordering processes, but how any changes to ordering types would affect ordering times.
Through our data exploration, we discovered that customers who used the mobile app to make their purchase spent more money per check but also saved time. This allowed our client to quantify the impacts of different ordering types across all their restaurants.
We then worked with the client to gather data from their data warehouse and performed a statistical analysis to determine current timings and general drive-through statistics. An in-depth root cause analysis was completed to discover and analyze hidden issues of the drive-through process.
The results were visualized and presented to business leaders in a clear way in order to expedite taking action.