Scheduling and Dispatching Optimisation

Gaining competitive advantage used to centre around product differentiation. While the products you rent still play an important role, the goalposts have shifted. To stand out, organisations are delivering services that exceed customer expectations, by improving the productivity and efficiency of thier field forces. And this means optimising scheduling and dispatching processes.

Even the best planned schedules are disrupted. For instance, urgent issues, unexpected traffic and customer cancellations can wreak havoc on a field force’s organisation. Regardless of the challenges, scheduling and dispatching still offer the best opportunities for improved efficiency.

There are two levels to consider. The first is the automation of decision making, which improves response times and reduces overall labour costs. The second is the use of machine learning (ML) to analyse historic data to enhance predictions for optimal routing and scheduling decisions.

Raise the productivity bar with AI

By using artificial intelligence (AI) to identify optimal resource allocation, organisations are able to dispatch jobs in a way that maximises first-time fix rates, ensuring customer satisfaction and reducing service-related costs. The ability to continually optimise a schedule as service requirements change provides many benefits. For instance, instead of leaving white space in the schedule when a customer cancels, an automated system will immediately assign an alternative task.

Another tangible benefit is the understanding of work urgency and service level agreements (SLA’s). When an emergency arises, low-priority work can be rescheduled to another time within the SLA window without adversely impacting customer experience.

While optimal automation cannot happen without AI, there is an additional advantage that can be delivered through the use of ML. A type of AI, ML uses historic data to improve the quality of decision making. One of the greatest attributes of ML is its ability to process large amounts of data.

Through ML, organisations can use data about previous disruptions to help with future planning. For example, ML can analyse historical weather conditions and when there is a higher probability of snow, the system can schedule lower priority jobs to preemptively mitigate scheduling disruptions, and therefore cancellations. In this way, field service technicians encounter less downtime, fewer work disruptions, and are consistently assigned jobs that match their skill sets.

When these technologies are strategically applied to connected equipment and sensor devices, valuable data about performance, environmental conditions and more is constantly transmitted and processed. ML analyses the collected data to preemptively identify issues before they even occur, avoiding downtime and saving time and money for businesses and customers.

Even the most experienced dispatchers and service managers have a limit to the number of variables they can consider when making scheduling decisions. With AI, calculations and changes are instantaneous, adjusting in real time to minimise disruptions and maximise the organisation’s desired outcomes and key performance indicators. And the majority of these changes can be addressed in the background, without the need for human intervention.

Key to providing superior customer experiences is communication. AI enables your team to share accurate arrival times with customers, as well as send details about the technician and their real-time status and location. This keeps customers informed and eliminates variables that can result in customer no-shows and last-minute cancellations.

Finally, as the use of Internet of Things (IoT) sensors increases, field organisations can be alerted to a problem before the customer is even aware. An alert can be sent to your field service management system and the schedule is automatically adjusted to dispatch a qualified service technician, while filling in any gaps that might occur due to the schedule change.

Removing the guesswork

Delivering on a service request means having to deal with the unexpected. Factors like last-minute cancellations, sick calls, changing weather conditions and shifting traffic patterns will always remain out of your control, and will inevitably impact field service operations. While these variables cannot be eliminated, they can be better managed through technologies like AI and ML.

The constant stream of inputs and refinements, and the feedback loop created by adherence to or deviation from the optimised routes and schedules, teaches your system to make better decisions in the future. It only stands to reason that the more data you provide, the more refined and focused your operations will be over time. The benefits of AI and ML are real and only getting better. So, what are you waiting for?

About the author

Paul Whitelam has more than twenty years’ experience leading multinational marketing and product teams. He has worked on both the technical and business aspects of many areas that are fundamental to field service. This includes senior-level positions at Nokia (mobility and sensor technology), HERE (mapping and GIS) and Endeca (data management and analytics).

Whitelam can be contacted on 0800 092 1223