Shipping delivery schedules were already being planned in the 1600’s between England and The Netherlands. Crates, barrels or other non-standard containment systems were used until the 1950’s when a standard shipping container was developed and later accepted as standard in the late sixties. This has been the most significant development until recently, but data is changing all of that. Even a small increase in efficiency carries huge benefits regarding efficiency, safety, and savings.
Airfare is segmented into a few different realms. There is commercial airfare, private airfare and air cargo. There is overlap amongst these segments. For clarity’s sake, the following solutions are segmented in travel and freight.
Get your ticket early. That’s the age-old piece of advice we all hear. But you’ll be surprised to learn that the best time to typically purchase your ticket is either 8 and 2 weeks before your flight. This useful tidbit doesn’t actually reflect reality. Ticket prices that vary according to a given flights demand are far more fair for consumers and lucrative for airlines. One must consider that a flight will complete its race regardless of whether or not it is at capacity; this has an effect on ticket prices but overall, data can be used to maximize booking rates , margins, and give thrifty consumers the chance to save even more by booking in advance.
Global consumption is not random. We can, with relative ease, predict demand for food, clothing, technology and other common items. Veblen goods are tied less to the economy and more to feelings and social behavior. But overall, we know how much people want to buy. Corporate purchases are less certain as the sales process last much longer and decisions are rarely made impulsively; strategic plans shed light on these plans in advance. Nevertheless, freight and logistic companies have even more data that just global trade at their disposal. Their entire history can be used to train models that predict demand. Moreover, idiosyncratic events that have some commonality with the past can serve as guides to dealing with future events.
Certain containers are intended for particular items. These may be liquid, hazardous or simply general purpose. The containers intended for specific usage such as liquid chemicals have longer turnaround times. They may also have to be shipped empty in order to be used because of a lack of niche demand in particular parts of the world. By optimizing routes, these containers’ down time can be minimized. And when such containers need to be washed and prepared, there will be less uncertainty as to their next intended client. Siemens recently invested in data science and has already seen returns You can also see a demo of how you would apply such a solution with Keras in shipping
Cities predict their public transits’ demand to determine how many buses or trains they need, where to build new lines and how often clients need their services. You can read more about smart cities in cation. Train companies work on similar problems, but usually abide by stricter schedules. There are obviously issues with other rail companies using particular tracks, but schedules are rarely so tight as to not leave room for change. Certain clients expect trains to run at a particular time, but planning the schedule without learning the behavior of passengers is inefficient. Companies can learn their clients’ behavior to better plan the number of cars they provide at particular times, increase or decrease the usage of particular routes and optimize their schedules to serve as many clients as possible, while minimizing waste.
Courier companies have been working on optimizing every aspect of their process to provide their services at the lowest cost possible. Companies like FedEx, DHL or UPS are constantly looking for room to improve. Smaller companies must be aware of such methods and react accordingly. In order to remain competitive, they must work on their own methods of optimization. A local produce supplier could save minutes a day by properly arranging his stock to minimize the time needed to unload it throughout the day. Savings of 15 minutes a day is the equivalent of almost 2 weeks of work time during the course of a year. Over the course of a year, this could mean 5-10% more business. If properly managed, additional customer would allow for faster growth resulting in a snowball effect that could dramatically change the trajectory of a company over the years.
Trucking is an interesting business. Just as in many aspects of society, a small portion of individuals look for their own personal gain at the expense of other. Fraudulent behavior, namely with regard to fuel costs companies millions a year. These costs are ultimately paid by the consumer leading to higher produce costs and decrease logistic efficiency. Economically speaking, lower transformational efficiency results in less cooperation, and ultimately, a weak economic structure. But such behavior can be identified.
GPS and IoT data allow us to monitor the behavior of a given truck. There are techniques that allow for fraud, but such behavior can be identified by sensors. Furthermore, modern logistic legislature mean that there are already countless sensors on a truck. This means that there is little work required for such insights to be extrapolated. All we need to do is take a look at data that is already being recorded.
Automatic Identification Systems have become standard over the past decade. They are officially mandated on larger ships but have become much more commonplace. When moving, vessels send their data as frequently as every two seconds and around every two minutes while anchored. Ships are expected to report on their predicted route, destination and ETA, but these are set manually and are often inaccurate. The journey a given vessel chooses can help us understand the potential destination it will be headed to. Machine learning in combination with this data can significantly improve vessel tracking.
Officially speaking, AIS data is supposed to include information relating to the planned destination. It would be quite nice if this information was up-to-date and provided a valid overview of destinations, but that is not the case. Thankfully, routes are fairly specific to particular destinations. Even on open seas, we can take advantage of historical data in predicting the statistical likelihood of given destinations. When, for example, a ship is transporting itself through the strait of Gibraltar, we have, at least to a certain extent, relative certainty of the list of potential destinations.
The crane – the most significant tool in a ports arsenal. These mighty tools are the main way of loading and unloading a ship. There is software that tries to optimize many aspects of this process, including load distribution, final destination, as well as trying to select the most optimal order to minimize load times. But there is a something missing, artificial intelligence, or as it is commonly known in tech, machine learning. Heuristic or rule based systems are currently used to optimize the order and location of containers during loading. The cold war taught us those heuristic systems are only useful for relatively simple tasks. And the scale of an entire vessels cargo is complex. The way this would work is actually quite simple to explain. First, we need to aggregate historic container data. We’d have an even easier time if we have data relating to particular cranes. This data can then be fed into either, an unsupervised system, where anomalies are automatically identified, and the algorithm makes sense of the data without human interference. Or, a supervised system, where we use said data to train our algorithm. Both of these methods have their benefits. In short, if we have a significant amount of data and complex system, then we should look to machine learning for increased performance.
Global trade is a marvel of the modern age. There are tens, if not hundreds of touch points involved in transporting items across the globe. When a ship approached a port, tides, traffic or weather issues occasionally lead to a ship being forced to re attempt docking after a few hours. Once a ship does dock, it needs to be unloaded, containers must be transported, pass customs if necessary, and get loaded onto their final delivery vehicle. Every step along the way has room for potential delays and issues. It is important, as a trader to be up to date in real time of the particulars regarding a given ship, its content and the containers involved. The most accurate way to do this involves taking advantage of AIS data and tracking IMO codes. Data science allows us to take this a step further and predict the types issues we might encounter.
The corollary to destination predictions involves the destinations themselves. When aggregating the predicted destination data, we are in effect taking a few steps into the future. Though this data is not 100% accurate, it still provides us with an adequate view to be able to gauge demand. This historical prediction is most useful for the short term. When considering the predicted demand of a port years into the future, we must adopt a different tactic. Economic drivers affect the demand for and supply of various products. Trade agreements and technological development further complicated this dynamic. Creating different models that take a particular look such factors and then coalescing them into a macroscopic view allows for the most accurate predictions.
The standard twenty and forty containers have been around for nearly half a century. In that time, they have eased the transport of billions of tons of cargo the world round. And yet there is still much room for improvement. First off, there are codes unique to each vessel, but it can be obstructed or damaged. Deep learning can allow us to recognize individual containers so as to improve tracking and minimize the number of containers that are lost in transit. Furthermore, increased monitoring could identify common points of failure and help optimize future workflows.
Predictive maintenance is a fascinating use case, as it can be applied across countless industries. The particulars come down to the specific component or system that is being monitored, but algorithmically speaking, there is a significant overlap. These kinds of algorithms are solutions that can help avoid catastrophes by identifying potential failures before they happen, as well as decrease maintenance costs by identifying subtle changes and component idiosyncrasies. Catastrophe prevention speaks for itself, but the savings from lowered maintenance add up and represent millions over a given product’s lifetime. Identify fuel consumption anomalies Fuel consumption is second to crew costs when looking at operational expenses. There are a few aspects in shipping where fuel anomalies arise. Firstly, we can take a look at potential malicious behavior. Skimming fuel happens. There are systems in place intended to counteract such practices, but the monitoring isn’t precise enough to catch every instance. The AI methods we mentioned above can be fine tuned to identify such behavior and even notice long term patterns. Such patterns can point out inefficiencies in our engines or steering behavior. Our engine may only need minor maintenance to provide a 20% increase in fuel efficiency, but how were we supposed to know otherwise.
There are either long held trusted suppliers that do their work well enough, but you have worked with them for so long that you find it hard to imagine actually changing. But are you sure about the quality of their work? Are they really providing you with the work that you are paying for? It’s worth taking a look at the work they have done in the past and compare it with other factors that may provide insight into their current quality, as compared to say their work when they were initially contracted or in relation to another crew working on similar problems. Insights from data are not the only indicator, there may be other factors you may not be aware of, so it is important to look for the causes of any issues before trusting blindly in data points.
VMS (Vessel Monitoring Systems) allow us to track fishing vessels within the economic exclusion zone of a given country or region. National laws and regulations vary, but overall, these kinds of systems are very useful for monitoring shipping vessels. They are much more accurate than AIS systems, as they transmit constantly. Taking year’s worth of data from an entire country’s fishing vessels gives a significant overview of the extent to which certain fish and certain areas are being farmed. Such an overview allows agencies and private companies to plan their fishing behavior for the future and to minimize the environmental impact.
Warehouses that stock inventory that will never be purchases are wasting their shelf space, but more importantly, inadequately forecasting their demand. Furthermore, proper forecasts can help reduce the chance of shelves being understocked by more accurately predicting demand. Such solutions apply not only to finished products, but also to the manufacturing and assembly process itself. Complex engineering products may travel hundreds, but more commonly thousands of kilometers before being completed. Inefficiencies quickly add up leaving much to be desired. Decreasing the number of steps is a manufacturing challenge, but being able to extrapolate the demand for particular components based on the finished products’ demand can serve as an idealized goal to aspire to and be used as an initial point of reference when train models and looking for additional room for optimization.
We’ve written an entire post on Dynamic Pricing. What we do is better reflect actual demand and allow consumers to take advantage of limited-demand products while allowing businesses to increase their profits for high demand items.
Amazon has shown that a conveyor belt worked for the third industrial revolution, but is not the most optimal solution for warehouses and factories of the fourth industrial revolution. Robots are only a small part of the solutions. To delve deeper into our Amazon example, let us consider the structured chaos that is item bin management. Things are not stocked on shelves based on their category, but are scattered in small individual bins that have been algorithmically optimized to provide workers the most optimal circumstances to quickly and efficiently find and package customer orders. Such solutions are not indicative of Amazon’s uniqueness, but rather their adoption of technologies that in the short-term cause creative destruction, lead to major improvements in the long run.
A fluid business that iterates on its processes and is constantly looking to reimagine its future is providing itself with the best chance of being relevant and profitable in the future. Companies that stand still are taking a step backward. Their competitors are not waiting for them to catch up. Land, Air or Sea, the method varies but the nervous system of global trade has begun taking advantage of Artificial Intelligence, or more specifically, Machine Learning and Deep Learning to optimize and automate their processes. Dynamic Pricing, Demand Forecasting, Route Optimization and Inventory Management are just a few solutions today’s technological innovations provide. Let’s set up a call to find out if your business is ready for the future.