ocean Archives

Predictive Analytics Comes to the Logistics Industry

Business Intelligence | By Steve Banker • 02/29/2016

Big Data has led to a discussion of predictive analytics in supply chain management. I’m not sure we have a good understanding in the field of how predictive analytics differs from forecasting.

Here is how I would differentiate the two.

All forecasting involves making a prediction, but not all forecasts are based on Big Data. Using historical data to make a regional forecast for most companies would not require Big Data. Forecasting demand at the store level probably would. The more inputs, the more granular the data, the more granular the forecast, the more we are in the realm of Big Data analytics. In short, when I hear predictive analytics I am apt to think this is a forecast based upon Big Data.

In logistics, we have not seen all that many examples of Big Data analytics. Using a demand forecast at the store level to create transportation plans –Terra Technology and JDA do this in different ways – would be two examples. Until recently, I would have been hard pressed to come up with another example.

That has changed. I recently had a conversation with Adam Compain and Will Harvey, the cofounders of ClearMetal. Mr. Compain is the CEO, Mr. Harvey is the Head of Technology. ClearMetal is applying predictive analytics to help Ocean carriers improve their profitability through better placement of ocean containers and more efficient vessel space planning. Even though the issue of Ocean carrier profitability is not at the top of my interests, the way ClearMetal is solving this sector’s problems is very interesting. And it is easy to see that many shippers may have deep data sources that could be mined in similar ways.

I’ll focus on ClearMetal’s container placement problem in this article. The company is endeavoring to make more accurate bottom up forecasts that go out 8 weeks on where containers are likely to end up and where they will be needed.

The company is using booking, container event, and vessel voyage data from carriers. They enrich this data by combining it with third party data such as currency rates, commodity trends, weather data, and other forms of data as well. They then create a chain of events to support an end to end shipment. If an electronics goods manufacturer wants to ship out of Minneapolis to the Port of Santos in Brazil, what is the probability distribution associated with having an empty container available in Minneapolis in eight weeks? Past order history for shipments into and out of Minneapolis, combined with commodity information (what goods are in those containers and is demand growing or weakening for those commodities) can help make that prediction. But containers into Minneapolis may have started as voyages from ports around the world. What are the chances (the probability distribution) these feeder voyages will be delayed at the port and intermediate rail heads?

The next step is to take the different supply chain lanes into Minneapolis and run simulations. There may be a certain range of chances that a certain set of containers that would eventually end up in Minneapolis will be delayed being unloaded at the port of Long Beach, delayed being loaded on the train in Long Beach, delayed in transit in Chicago, etc. Different estimates are used: a one day delay at Port of Long Beach is one simulation event, one day quicker through Chicago than expected is another, and so forth until millions of simulations are run.

Clearly this is a Big Data solve. It is interesting math. And it could provide a lot of value to Ocean Carriers that have been facing tough economics for years.

Does the math work? ClearMetal says it does. Based on some pilot engagements, top ocean carriers are telling them this solution has the potential to save them tens of millions of dollars in reduced container inventory. They believe they have also proved they can enhance revenues by making sure containers will be in the right location to support door to door deliveries.

But whether ClearMetal succeeds in the market or not, it is clear that interesting, new predictive analytic solutions will increasingly be available in logistics.

Dell and Caterpillar Reduce Freight Costs with Mode Shift

Transportation | By Steve Banker • 10/28/2013

The CSCMP Annual Global Conference, the most important supply chain conference of the year, had some nice mode-shift case studies. Speakers from Dell (Rob McIntosh, Global Reverse Logistics Director) and Caterpillar (Tom France, Director of Global Transportation) shared their insights and experiences last Monday.

In the case of Dell, a manufacturer of personal computers (PCs) and other electronics-based technology products and solutions, the shift meant moving from flying international bulk air to increasingly making use of 2 to 5 day air, rail (particularly in China), and ocean. This shift would not have been possible without a shift in business strategy.

Historically, Dell’s supply chain was famous as a build-to-order (BTO) manufacturer. Customers went to Dell’s website and ordered exactly the components they wanted in their PC. The result was a very fast and responsive supply chain with almost no inventory. However, as the prices of PCs fell, and PCs became ever more powerful, customers no longer felt the need to wait a few days for a specially-tailored PC. They went to retail outlets and bought cheaper products off the shelf.

Dell responded by moving to a segmented supply chain. One segment involved selling lower cost products based on a smaller number of configurations (approximately 300) directly to large retail chains. This involved shifting a large portion of the production from BTO to make-to-stock (MTS). Once Dell became a MTS manufacturer, forecasting and customer analytics (what do customers want and what will they pay?) became more important, and the supply chain slowed down. The company now holds more inventory, but it can also engage in much less costly and greener modes of transportation.

Caterpillar (CAT) is the world’s leading manufacturer of construction and mining equipment. Tom France of Caterpillar made an interesting point. When supply chain professionals think of mode shift they think of moving from faster and higher cost modes, like truckload, to a totally different mode, like rail. But you can also stay in a mode and achieve the same thing. In CAT’s case, that meant moving from flying spare parts overnight to using many more 3 to 5 day flights where customer expectations were aligned on a lower cost, but slower, delivery.

At CAT the ability to utilize lower cost modes has been facilitated by technology. The company built a control tower, using a visibility solution from GT Nexus, to achieve end-to-end visibility. This tool allows it to measure not just carrier lane performance, but also the variability associated with different carrier’s performance on specific lanes. What this means is that a carrier that delivers a number of shipments five days early or late has higher variability than a carrier that consistently delivers within a day or two of the scheduled arrival time, even if on average its on-time performance is the same. Lower variability translates into a lower need to carry inventory.

CAT also uses a number of air and ocean transshipment hubs. These hubs give it better scale on a lane. With scale CAT becomes a more important customer that can pre-book ocean capacity with no dwell times. In the air mode, it ships hub to hub to maximize cube.

CAT got the visibility solution up first, then put the hubs in place. Tom believes that was the right approach because putting in a robust process based on “trusting but verifying” what their 3PL companies were telling them needed to proceed changes to the network.

And at CAT, the question of what customers want and what they will pay also influences what sorts of modal choices it makes on a product by product basis. Tom made the point that engineering $400-500 out of a product is almost impossible. However, in a global supply chain with heavy equipment products, achieving this with a lower-cost mode is quite doable. Transportation can be a “huge lever” in lowering products costs. It is just a matter of working with customers on the price/delivery tradeoffs.

In conclusion, one of the things that most struck me was Dell’s business strategy transition. Much of the rhetoric in supply chain management today is about becoming “demand driven.” The poster child for this was the old Dell. There is no better way for a manufacturer to get demand signals directly from the customer, and then reacting to those demand pull signals, than engaging in a MTS e-fulfillment supply chain. Dell’s experience shows that sometimes survival involves becoming less demand driven.

Ocean Contract Management is Complex

Transportation | By Steve Banker • 03/12/2012

One choice international shippers face is whether to sign long-term contracts with ocean carriers or use freight forwarders and pay spot market rates. In the current environment, spot market rates are often lower, but shippers may face a service penalty when capacity tightens. Just as airlines overbook, so do ocean carriers. However, while airlines reward those who give up their spot, ocean carriers don’t. In an overbooking situation, ocean carriers are likely to reward shippers that have long term contracts with better service.

Shippers that decide to move a portion of their freight using long-term agreements will quickly learn that ocean contracts are complex. There are dozens of ocean carriers that cover different lanes, plus a multitude of different surcharges, including charges based on commodity type, and minimum quantity commitments.

Matt Motsick, the CEO at Catapult International, and Alicia Canelos, Director of Managed Services for Ocean Rates, talked to me about the complexity surrounding surcharges. Catapult has IT solutions and special expertise in ocean freight audit.

Matt and Alicia told me that ocean contracts are notoriously complex, with each carrier contract being very different in format and content. On the content side, each carrier has different surcharges and applies them in different ways. There are 367 different surcharges worldwide according to Catapult, and a large percentage of them are port charges. There are many different types of port charges, and every port charges a different amount for their services. For example, some ports have theft and recovery charges. Also, the vocabulary surrounding surcharges is not standard — what shippers are used to calling “fuel surcharges” for over-the-road transportation, ocean carriers call a “bunker contribution charge” or a “bunker adjustment factor.” Further, the surcharges are listed in different places in the contract. If you’re a cynic, you might say a carrier’s goal is to confuse customers.

There is a modicum of good news. The Federal Maritime Commission requires ocean carriers serving the US to publish all tariffs and surcharges. In theory, these are publicly available online. However, to find the web page, discover the surcharges, and apply them to the contract is a time-consuming task at best.

Shippers frequently seek to negotiate long-term contracts with fixed surcharges so they don’t have to constantly adjust rates in their transportation management system (TMS). Often the goal is to include as much as possible in the fixed rates, sometimes including fuel surcharges. But buyer beware! For a carrier to sign this, they have to charge a premium to cover their risk. The more surcharges included, and the more those different surcharges are apt to change in price, the higher the risk premium will be.

There is also complexity around commodity pricing. I talked to Ivan Latanision, Senior Vice President of Product Management at INTTRA about this aspect of ocean contacting. INTTRA offers a multi-carrier e-commerce platform that facilitates the communication between ocean carriers, freight forwarders, and shippers. Ivan told me there are historical reasons for commodity pricing. Before ocean containers were introduced, port workers had to break down bulk loads. Th difficulty in performing this task varied by commodity type, so it was reasonable for longshoremen to be paid differently based on what was unloaded. But while the task of breaking bulk has largely disappeared, these commodity-specific royalties remain.

According to Kim Le, the Director of CargoSmart North America, the commodity naming conventions are not standard. One carrier might call a commodity in question a “car,” a different carrier might call it an “automobile,” and a third carrier might call it a “vehicle.” This can make apple-to-apple comparisons difficult.

But Kim also says the lack of standardized naming can work to a shipper’s advantage. It might be that a commodity could be fairly labeled in one of two ways. Naming conventions are not always black and white. This is particularly true in certain commodity classes like furniture. In this case, the shipper can choose the commodity with a lower fee associated with it. Carriers, because of their excess capacity, are more willing to be flexible. Shippers who have visibility to the rates of associated similar commodities in their contracts have greater flexibility to book cargo against the lowest rates available.

Kim’s company, CargoSmart, offers an e-commerce platform focused on ocean transportation. CargoSmart provides solutions for shippers and logistics service providers to manage their ocean carrier contracts online. The solutions automate the complex process of preparing for negotiations, making optimized bookings against contracted rates and routes, and reviewing carrier performance throughout the year.

Finally, there is the issue of minimum quantity commitments. If a shipper commits to move a certain quantity of goods on a lane with a particular carrier, they need to track that and meet their obligations. If they don’t, they face penalties. If a shipper has committed to different volumes for different carriers on a lane, the tracking of these “allocations” becomes more difficult. A good transportation management system automates this allocation tracking process.

Ocean contract management is complex. But by using a robust TMS, domain experts, and other ocean-specific solutions, shippers can make more optimal decisions.

A complete analysis of logistics trends, technologies, and services

Archives

Login