ACREW: Adaptive Crew Response Engagement Work-engine
Author’s Note: The topic of this white paper illustrates a proposed solution to solve complex scheduling issues associated with national and international transportation. While this solution does not current exist out-of-box, the foundational components that would power it currently exist and have been successfully deployed in a production environment.
The Adaptive Crew Response Engagement Work-engine (ACREW) would offer a distributed platform leveraging next-generation predictive analytics to negotiate efficient crew interchanges across a transportation company’s entire network. The platform would maintain an optimized availability pool, so there would never be too many — or too few — employees scheduled for a run, keeping “Dead Head” crews to a bare minimum.
ACREW would monitor multiple data sources in real-time (weather, train schedule, current events, crew status, operations, construction, traffic conditions and so on) and combine these in-flux variables with the more consistent variables (E.g. consists, crew history, seasonal considerations). The real-time, constant re-evaluation of these variables would allow ACREW to accurately predict the next optimal interchange along the route, and begin assembling the crew for the next shift.
Once ACREW would establish an interchange point, it would begin not only assembling the crew, but also contacting your ancillary support partners (E.g. limos/vans/hotels) and arranging travel to and from the interchange point, as well as arranging hotel accommodations. While in transit, ACREW would track these assets as they converge, assuring that both the employees and the transportation service arrive on time and in the right location.
While putting the next interchange crew together, ACREW would evaluate a variety of factors, including, but not limited to: employee status, territorial qualifications, skill set, compatibility with other crew members, union rules and federal regulations. This means that not only would the next crew be in place, but it would be the ‘best’ crew possible for that particular interchange point.
Managing a nationwide network of trains, yards, tracks, trucks and other hardware is most certainly a challenge, but perhaps managing the human element is the most challenging of all. Capture Club understands that the human element is precious, and needs to be managed in a sensitive nature, evaluating a great many factors in order to insure that this fragile component of the network is handled with the greatest consideration possible.
Given the constant state of flux, the precious cargo, the human element and the network of hardware, ACREW wouldn’t just take a reactive approach to interchange prediction, it would take a pro-active approach. While evaluating this constantly evolving environment, if ACREW would encounter a ‘red flag’ warning (E.g. train running behind schedule, a wheel bearing heating up beyond normal limits, a severe storm or inclement weather ahead) it would begin running “what if” scenarios in the background, so that if a problem would emerge, the steps required to resolve it are already at-hand.
The Capture Club team has a combined 40 years experience in solving mission critical problems in the areas of Machine Learning and Predictive Analytics, as well as providing best-in-class solutions that effectively solve problems just like this one.
Use Case: A national or international corporation has a transportation line that requires (in part):
- Multiple crew interchanges along the route
- Crews with certain skill sets and territorial qualifications
- Crews that work well together
- Crews that may be assembled on notice for emergencies
- Crews that need to be in the right place at the right time.
- Crews that are subject to union and/or federal regulation constraints.
- Crew members whose status indicates that they are available.
- An optimized availability pool for every interchange location.
Solution: ACREW Predictive Scheduling. This would take into consideration the following (included, but not limited to):
- Cargo type
- Crew member status
- Weather conditions.
- Traffic Conditions
- Seasonal Adjustments
- Hazardous material considerations.
- Current News Events
- Travel Conditions
- Crew compatibility
- Crew skill sets
- Transportation type
- Relevant Federal, State, Union rules and regulations
ACREW would then apply proprietary predictive analytics algorithms to this data to assemble an optimized crew for an interchange point, using the aforementioned criteria, and complete with depth redundancy; ACREW would then notify and assemble an appropriate crew to be on site at the requisite time, and prepared for the requisite role. Once notified, the system would track the user until they arrived on site, and could potentially notify substitute crew members should one en route encounter difficulty (E.g vehicular trouble). It would also notify downstream support businesses and request travel and/or accommodations, depending on the interchange point.
Related Case Studies: