As technology develops, we are expected to leverage it to its every capability. We are expected to search harder, dig deeper, and do more with the information that we [do not] have. Organizations are expected to read their customers, and determine what they are going to do, before they do it.

Years ago this was a shot in the dark. Today, with data collection and analysis becoming standard, we can better predict the actions of our customers. Organizations are able to collect massive amounts of raw data, but it is just simply that, raw. Data cannot tell us much in its raw form. It is not until data is analyzed that it becomes information and then knowledge that users can obtain. Analysts can then take this information, and knowledge to make predictions. What could happen? This has been predictive analytics. Now, with prescriptive analytics, the game has changed…

Predict vs. Prescribe    

Predictive analytics are all about making educated guesses about unknown, future events, based off of historical data as outlined by Prescriptive Analytics Today. Prescriptive analytics takes it to the next step, by acknowledging the possible decisions, and then making recommendations based on them. With various parties in the mix we need to be able to customize our message and recommendations based on the industry. Let’s say that last Friday you bought a burger for dinner using an interact or credit card. This Friday, you may get an e-mail or push notification from the same restaurant, suggesting that you stop by. This technique goes beyond predicting that you may eat burgers on Fridays. It goes to suggest that you should get a burger this Friday because you got one last Friday or because you are nearby, as per your location services.

Prescription Analytics in Ports

With any sort of analytics one needs data. It is the same for the use of prescriptive analytics in ports. Over time, data is collected on various activities in and around the terminal. For example, when trucks come into the terminal, when they leave the terminal and their behaviors within. Based on the various times and resources that are transported, schedules can be made to optimize time. The overall goal here is efficiency and that is exactly the result with these analytics. With this data and systems that are constantly learning, it has the potential to not only predict late trucks and no shows, but act on it. Also, by knowing which trucks are in the queue and picking up what, the terminals can better plan and reduce unloading time.

Prescription Analytics on Roads

The same can be done for the roadways, in the monitored areas. The roads are important for the movement of not only people but goods. Their timely arrival is an essential part of the supply chain. When there are accidents on the roads or general congestion, drivers can and should be notified and prescribed a different route in advance so that they are able to avoid the congestion. It may communicate the times to get to various points, based on other motorists up ahead that have just travelled that path, based on V2V communication or through crossing checkpoints.

Prescription Analytics at Borders

Borders are infamous for their long wait times. Selecting which lane to get into when crossing is another battle – some are much faster than others. If a computer could collect data, make predictions based on the data and suggest an itinerary for crossing the border, it would take the guessing out of it all.  “Leave your house at time x, and take this route. That would have you arriving at the border at time y, which is your scheduled time. Follow the instructions and go through lane z. Then continue on the recommended route to your destination.” What was once a stressful situation is now viewed as simple and easy.

Organizations will adopt this new era of prescriptive analytics as it has the potential to increase efficiency. This is saving time, money, and the environment in this case, without idling. With tools like predictive and prescriptive analytics organizations will be able to do just that. As technology advances, analytics and its capabilities will evolve. Systems are constantly learning based on its exposure, commonly known as machine learning. Not leveraging technology to its every ability is a thing of the past. Systems now a days are catching patterns and trends that we may not catch right away or even at all!