Analytics in Logistics Explained
Descriptive, predictive, and prescriptive analytics in the context of logistics — how and why to use them.
Big data and predictive analytics are among the most talked about applications of technology in logistics right now. Yet, despite all the attention it can be difficult to understand these ideas in practice. The problem is there are not a lot of actual use cases available to clearly explain their value to logistics companies.
While predictive analytics is the most commonly used term, it’s really just a catch-all for the three types of analytics companies are employing to gain insights for business intelligence. In addition to predictive, the other two types of analytics are descriptive and prescriptive.
To better illustrate the three concepts in the context of logistics, consider these examples of a trucking company looking to use data to improve the efficiency and profitability of its linehaul operations.
Descriptive Analytics is the exercise of looking backwards to see and understand what has happened in the past. To a truckload carrier, the value of descriptive analytics is an understanding of how full trucks were and, more importantly, how well the space was used.
This is an important distinction, because knowing a truck was shipped 70% full is meaningless without considering the volume and weight density of the truck’s contents.
To illustrate this concept: picture the difference in space utilization on a truck between a small, lightweight pallet of a material like corrugate that cannot be double stacked (and generates little revenue) compared to a stable, dense pallet of canned foods that can be stacked in multiple layers. Descriptive analytics explains the impact of these differences.
Predictive Analytics is the practice of estimating the future. Building on the previous example: a trucking company can apply predictive analytics to plan capacity more efficiently on its trucks. This is achieved by predicting the types of products that will be shipped, and therefore identifying opportunities to increase cargo density and loading factor.
The benefits of this technique come from the ability to anticipate the types of products that will be shipped and where they will be going. Key inputs and historical data are required to make these predictions.
To use predictive analytics in your logistics business, consider historical information like shipment types, weight, origin/destination pairs, lead times, and equipment types, and make educated guesses to fill in gaps in the data. The output is a forecast of how many and what types of shipments are expected for each destination with the likelihood of that scenario happening.
Prescriptive Analytics prescribes the action to take on the basis of the information gained from the previous two sets of analyses. In practice, this provides the insight to the truckload carrier to know how to better combine cargo on trucks to improve the load factor.
It creates other actionable insight as well, such as advance knowledge of which planned trucks will be empty, so they can be cancelled; advance notice of when extra capacity will be needed; and the ability to price more accurately. Prescriptive analytics is where the ultimate value of analytics is derived.
For logistics companies, the advantage of using data in these ways is clear. The business value is significant. However, the process of using analytics takes experience and needs to be rooted in proper expectations
It’s important to recognize that data science is complex and prediction in its own right is not always useful. But gaining and using the knowledge that there is a greater or lesser probability of certain scenarios happening is a powerful operating advantage.