Using Data to Build a Better Last Mile.
Join Stephen Saldate, Operations Analyst with beverage distributor Doneghy Sales; and Wise Systems Solutions Engineer, Jacob George; Customer Success Manager , Hiba Zakane; and Product Manager, John Durst as they discuss how to build a better last mile with data. Check out some Q/As from the interview (edited for brevity and clarity).
Question: What are the most common data challenges that companies run into when tackling a routing and dispatch software implementation?
Answer: I think there are multiple pieces that must be considered in terms of what data would come into play when building out optimal routes. These include customer delivery windows, driver shift times, drop off location, etc. Often this information is within an organization, but most likely distributed with different stakeholders. Another piece is partial data sets. Maybe you’ve got the visibility to track your vehicles on the day of the delivery, but do not have enough data to tell you whether deliveries have happened or when they’re expected to happen. Or, to understand the customer’s perspective regarding ETAs.
Question: What do you think is the most important piece of last-mile data for an organization to think about or pay attention to?
Answer: It could be anything that could possibly impact your operations or clients. Start out basic, try to figure out what you normally use to predict your performance (points of deliveries, addresses, obviously time windows and their accuracy, on-vehicle inventory details, on-time percentage, vehicles and drivers).
Question: How can I provide a more detailed ETA if I only have an address?
Answer: Even with just an address, we can use real-time on-the-road data like traffic from Google (HERE, Waze, or Apple Maps) to calculate the time it will take the driver to get from point A to point B. We can also include anticipated service times in the calculation, taking into account data points like the number of packages in the delivery or seasonally averaged times.
Question: What do you recommend an organization do or think about in regard to their data before starting on a last-mile platform integration project?
Answer: I think the biggest thing is understanding your goals and what you want to do with the data. It’s great to have all the data in the world, but if you’re not sure what to do with it, or how it’s going to help your company, it is kind of useless. So, understanding what your goals are prior to working with the data is key – whether they’re maximizing fleet utilization, or lowering operational costs.
Question: Why is clean data so important in machine-learning applications?
Answer: Having clean data is very important. If you’re getting a lot of noise in your inputs, or noise in your outputs, it can really change the outcome of any kind of prediction that you make.
Question: I’m curious if anybody has any examples of what happens when bad data is used?
Answer: In route planning and optimization, bad data will have a direct impact on the shape of the routes, which will lead to poor route execution. This has a direct impact on your bottom line.
There’s much more to discover. So, watch the webinar then reach out for a demo of the Wise Systems delivery automation platform to see how you can build a better last mile using data.