Personalized service is a fundamental principle of Grange Insurance’s business model. The insurance provider maintains a network of more than 3,600 independent agents who provide local, person-to-person interactions for Grange’s home, auto, life and business insurance customers. This DIY, hands-on approach is a selling point for its customers, but it become a problem for its contact center teams. Staffing was decentralized, and none of it was automated. The complex, roundabout spreadsheet-powered forecasts had limited accuracy, reducing service levels. Determined to excel in customer satisfaction across channels, Grange implemented a workforce management and forecasting solution to update and improve its contact center operations.
The results were extraordinary. The new system’s superior forecast accuracy dramatically improved service levels, from 58 percent to more than 80 percent. The inclusion in the new forecast of detailed historical data as well as multi-skilled agent availability made Grange’s staffing levels a much better fit for actual call volumes. It was a solution that delivered results far beyond the capabilities of any spreadsheet.
Forecasts and predictions
The term forecasting usually refers to shorter time projections, such as those over a span of hours, days, weeks or months. Predictions, in contrast, belong in long-term planning -- often years in advance. Forecasting is most effective with large caches of rich data containing patterns that are likely to repeat. An accurate forecast balances supply (agent availability) and demand (call traffic). When callers outnumber agents, wait times rise and overworked, stressed agents become frustrated; when agents outnumber callers, profitability decreases. Forecasting and workforce management allow organizations to project a happy middle so employee schedules can be optimized days, weeks or months in advance.
Though the concept is simple, the execution is anything but. Modern forecasting systems can handle incredibly complex demands, weighing and incorporating any range of source, input, and historical and real-time data. They may, for example, automatically collect historical data from all contact sources including automatic call distributors (ACDs), outbound dialers, multi-channel routing platforms and back-office employee desktops. They can accurately calculate resource requirements by taking into account the exact routing rules, agent skills and work rules of a contact center environment with multi-skill simulation. They can be adjusted for special events and holidays. The best can even prepare for the impact of intraday change – all in accordance with custom-defined metrics and outcomes.
A golden age of predictive analytics
These capabilities are linked to ongoing developments in machine learning and artificial intelligence. We are living in a golden age of predictive analytics, and forecasting and predictive technologies are revolutionizing business well beyond the contact center. In healthcare, proper staffing has heavier implications than customer satisfaction and profits: It can be a question of life or death. Forecasting strategies can enable hospitals to manage schedules for nurses and other support staff, predicting the flow and arrival patterns of patients in the emergency room. These configurable models can be adjusted to assign more weight to certain data, and the models learn to adapt to seasonal, weekly or hourly patterns without human intervention. The benefits are multifaceted: Patients spend less time in the waiting room, management saves on salaries, employee satisfaction goes up, turnover is reduced and lives are saved.
Perhaps few customer-facing industries rely on analytics more than commercial air travel does. The industry is ideal for forecasting technologies, because it yields vast amounts of data and offers countless potential variations and adjustments. Airline data strategists process thousands of flights, hundreds of airports, millions of passengers, a combination of economy, business and first class rates, oil prices, weather, holidays, seasonal and weekly changes, delays and more. These analyses forecast the optimal flight routes, schedules and prices. Airlines tweak and adjust fares, and estimates indicate that the largest ones make millions of price forecasts a day. Schedules and routes are rearranged and moved to optimize profitability. While the true value of these capabilities is uncertain, airlines with outdated or sluggish systems now lose billions a year due to their technological handicap.
The use of forecasting and predictive technologies is ballooning. With more data and more processing power than ever before, these tools can calculate resource requirements with unprecedented accuracy. In the competitive world of contact center management, that difference can provide users with an edge that spreadsheets will never allow. And as data records and processing power grow, our ability to apply them and forecast will only continue to improve.
Paul Chance is a senior product marketing manager for NICE Workforce Management (WFM), the leading software solution used by contact centers to digest the complexity of their organizations and produce precise forecasts and clear action. For more information, visit www.nice.com/engage/workforce-optimization/workforce-management.