Actions and Detail Panel
Forecast Performance Measurement and Value Added - LCF Workshop in London
Fri 24 March 2017, 13:00 – 17:30 GMT
** Although this Workshop is free of charge, places are limited, so booking is essential **
Forecasting is essential for many business processes. However it is not always easy to measure the forecasting performance and asses the value of forecasts. The event will bring together well-known practitioners and academics to present, hear about and discuss new insights and approaches to support topic of Forecast Performance Measurement and Value Added.
Programme of the event
The programme can be downloaded from here.
Charles Chase (Executive Industry Consultant, SAS, United States);
Title: How Efficient is Your Performance Metrics Process?
Abstract: Measuring forecast performance is critical to improving the overall efficiency and value of the demand forecasting process. There are two distinct purposes for measuring forecast accuracy: (1) to measure how well we predicted the actual occurrence or outcome, and (2) to compare different statistical models to determine which one fits (models) the demand history of a product and best predicts the future outcome. The methods (e.g., MAE, MPE, MAPE, and WAPE) used to calculate forecast error are interchangeable for measuring the performance of a statistical model as well as the accuracy of the prediction. The most common performance metric used across all industry verticals is MAPE (mean absolute percentage error), which pays little attention to the forecastability aspects of the demand process efficiency. FVA is truly an innovation in business forecasting that is being widely accepted as part of a company’s standard performance metrics. The FVA performance metrics are a proven way to identify waste in the forecasting process, thus improving efficiency and reducing cycle time. These topics and others will be discussed in detail during this session.
Bram Desmet (Managing Director, Solventure, Belgium);
Title: The impact of business strategy on forecasting and forecast performance
Abstract: Bram is working on a book called 'Supply Chain Strategy and Financial Metrics'. With the 'Supply Chain Triangle' he captures the supply chain struggle of many companies in balancing service, cost and cash. Improved forecasting is a cornerstone in improving that balance. He shows how different business strategies (e.g. cost, versus product leadership), lead to different trade-offs in the triangle, and to different forecasting challenges. Using cases from high-tech and retail he illustrates how different strategies come with different levels of complexity. When benchmarking forecast accuracy (and supply chain KPIs in general), accounting for that strategy is crucial, not to compare apples to pears.
Marina Sologubova (Senior Manager, Demand Planning & Supply Network Planning, Johnson & Johnson);
Title: Forecasting Performance Measurements and FVA at Johnson & Johnson
Abstract: Nowadays with the increased market volatility organizations are struggling to meet their forecast accuracy targets. Traditionally those targets are being set based on the historical performance or benchmarking with the other businesses. However, there are so many more aspects that are not being considered resulting in unrealistic targets. Forecast value add (FVA) methodology helped J&J to establish the baseline, bring objective perspective and identify key improvement opportunities. It also allowed us to continuously monitor performance of the statistical forecasting applications and decouple it from the work done by the demand planners. Over the course of last year we successfully applied forecast value added methodology across different business units/regions within Johnson & Johnson that led us to key opportunities in the area of demand planning (People, Process, Technology) to focus on in the future.
Title: Benchmarking International Forecasting Performance from Errors towards Value-Add at Beiersdorf AG
Abstract: Beiersdorf has tracked forecast accuracy on a monthly basis across their large assortments for over a decade. However, with markets growing more competitive and internationally more heterogeneous, these final errors did not provide insights into what was actually driving forecast effectiveness: good statistical forecasts, good expert judgment, or merely changing market volatility. To provide guidance on best-practices, BDF is in the process of introducing a Forecast Value Added Analysis (FOVA) of measuring statistical forecasts and the judgmental adjustments relative to a Naïve benchmark for all products and each country. In this talk attendees will learn how to conduct an Extended FOVA analysis, and how to extend it into an operational setting. Moreover, we will share some insights into pitfalls in introducing FOVA.
Drawing on their expertise in data-driven strategies, including predictive analytics, the participants will share the newest, impactful, and innovative ideas, experiences and tools with business attendees.
The workshop will provide forecasting professionals with the opportunity to turn sophisticated forecasting models into real-life, useful insights delivering more effective forecasts.