Skip to main content

A guide to predictive field service

(Image credit: Image Credit: Razum / Shutterstock)

Thanks to today’s digital marketplace and the on-demand services it facilitates, customer expectations have increased to unprecedented levels. This trend is underlining the importance of communication and timely delivery of service, with a presumption of minimal waiting and a speedy resolution for any issue that may arise. Successful service organisations are meeting and exceeding customers’ expectations with optimised scheduling, which automatically accounts for both the customers’ and the service business’ preferences when coordinating appointments. As a result, work is executed at a time that is convenient for both parties, eliminating premature maintenance and the productivity loss that ensues.

While there are dozens of elements that influence the outcome of a service call, few actually fall within the technician’s control. Predictive field service offers companies a way to forecast disruptions or delays before they happen. With the right data and intelligent technology, it is possible to be ready for the unexpected and avoid letting disruptions threaten productivity. Predictive scheduling uses artificial intelligence (AI), machine learning and data science to increase schedule accuracy and ultimately deliver better service to customers. Creating a more accurate schedule helps reduce the unknowns so service technicians can focus on the job at hand without having to worry about factors outside of their control, such as traffic and weather. Customers are happy because they receive proactive updates about the status of their service visit with accurate technician arrival times so they are not stuck waiting at home for hours at a time. 

The need for increased quality of service is not a new concept, but what is new is the disparity between what companies say they deliver and what they actually deliver. Eighty per cent (opens in new tab) of companies believe that they deliver a “superior experience”, versus only 8 per cent (opens in new tab) of customers who agree. To address the disconnect between companies and customers, companies must understand their customers’ preferences and provide exactly what they are looking for. Today we have AI-powered applications to sift through insurmountable data and help minimise the gap between planned versus actual, which means fewer late arrivals and missed appointments, and less customer time spent waiting or rescheduling. With artificial intelligence learning and growing smarter every day, the possibilities for predictive field service are endless.

Establishing reliability

In field service, one missing element in customer experience is reliability. A recent report (opens in new tab) found that the best performing companies have deprioritised operational metrics in favour of customer satisfaction metrics when evaluating field service performance. Other research (opens in new tab) found that 58 per cent of respondents said the use of technician tracking technology would “somewhat increase the likelihood” of hiring a field service company over another, and 28 per cent said it would “greatly increase the likelihood” to hire that company. Flexible scheduling, visibility into a technician’s location, and streamlined communication help improve the customer experience.

While daunting, these expectations are achievable if companies prioritise the collection of data that supports capabilities like predictive job duration, predictive customer cancellation, predictive first-time fix, and predictive parts management.

A crystal ball for field service… almost

No matter how skilled a technician, without the right parts or tools, a first-time fix is impossible. Predictive parts management means that field service organisations keep track of parts data (opens in new tab) to ensure a technician is always fully prepared before heading to a job site. Sometimes a customer might describe a problem in one way, and it turns out to be a completely different issue when the technician arrives onsite with parts to fix the problem described, but not the actual problem. However, by tracking parts data and job history, predictive technology can ensure you are prepared for anything. For instance, if there’s a history of customers calling in with a particular problem and misdiagnosing it, machine learning solutions can recognise this and make sure that the tech has the right tools and parts for either scenario. This minimises the consequences of traditional parts management solutions, including repeat visits and poor customer satisfaction scores.

With the power of predictive field service, it is possible to keep your business running smoothly, despite unforeseen obstacles. Intelligent technology can automate and optimise business and scheduling decisions to minimise the efforts of the dispatch team, and free them up for more strategic exception handling. As long as you consistently track relevant metrics and operationalise machine learning technology, you can meet customer expectations without overspending or sacrificing your business goals.

Predictive job duration calculates the most accurate time it will take for a technician to complete a job, based on all relevant job details and technician information. In other words, it forecasts how long it will take a particular technician to successfully complete a specific job. Having this information during the scheduling process helps maximise the productivity of your workforce, without over or underutilising resources.

While legacy solutions only consider whether the technician has a particular skill or not, and allow for static job durations, predictive solutions factor in technician skill competency using historical job data to automate the assignment of accurate job durations. This includes a particular technician’s past performance on a specific job type or time of day, as well as other pertinent details. Using actual and individual performance data, based on multiple scenarios is much more accurate than using averages, and leads to optimal decisions for your business. This is referred to as ‘Actual Intelligence’.

Predictive customer cancellation is another piece of the puzzle that decreases disruption by considering both structured and unstructured data in its calculations. Structured data includes weather patterns, time of day, and customer demographics, while unstructured data includes dispatcher notes and customer history. A smart field service management solution can leverage this data to automatically avoid scheduling certain jobs when a customer is most likely to cancel. For instance, let’s say a meter replacement is scheduled at an office during business hours. The business owner might not have been aware that power needs to be shut off during the replacement, and cancels as soon as the tech arrives and informs her. On the other hand, predictive technology would consider this factor and only offer appointment times outside of regular business hours.

The average first-time fix rate for an organisation is approximately 77 per cent (opens in new tab). That means that about 23 per cent of all service calls require a second visit or more, and the customer has to set aside more time to wait for the technician.

With predictive first-time fix, it’s possible to calculate the probability that a particular job will be fixed the first time, based on the technician assigned. In other words, by factoring in individual technician skills and job data, you can determine the likelihood that a particular tech will be able to carry out a first-time fix. Reducing repeat visits is crucial for increasing customer loyalty. It shows your customers that they can always count on you for a quick, seamless resolution to their problems.

Steve Smith, vice president of strategic industries, ClickSoftware (opens in new tab)
Image Credit: Razum / Shutterstock

Steve Smith is VP of strategic industries at ClickSoftware.