In a global economy marked by fragile supply chains, scarce resources and rising energy costs, the spotlight is on forecasting to address these issues.

In 2022, McKinsey & Company uncovered a staggering $600 billion annual food waste, equating to 33% – 40% of global food production, spotlighting the devastating consequences of poor planning. Accurate and timely forecasts are now crucial, serving as a key driver of operational agility and sustainable growth.

Forecasting today: A cornerstone for success

Forecasting has been a valuable tool for organizations, creating effective planning and informed decision making. For example, in the consumer-packaged goods industry, the McKinsey Global Institute's insights highlighted that a 10% – 20% accuracy improvement in forecasting could yield a 5% reduction in inventory costs and a 2% – 3% revenue increase. However, forecasts must be accurate and adaptable to continuous shocks as the economy changes for organizations to stay resilient and competitive.

3 key areas of evolution for forecasting

As technology advances, the future of forecasting promises to be more sophisticated yet intuitive and accessible. Forecasting software companies are poised to lead a paradigm shift, focusing on three key areas:

  1. Improving data quality: Advanced feature engineering techniques and integration with enterprise resource planning (ERP) and Internet of Things (IoT) systems will provide a comprehensive, real-time view of business operations. Model operations (ModelOps) will evolve to streamline end-to-end forecasting processes.
  2. Cloud-based analytics: Democratizing forecasting through cloud-based analytics consumption models will ensure organizations use what they need when they need it. Forecasting automation will optimize both computational intensity and forecasting accuracy at the same time.
  3. Configurable systems: Open, extensible and configurable systems will keep pace with the fast development of new methodologies and algorithms. This flexibility caters to evolving customer needs and diverse programming languages.

How generative AI will change forecasting

The recent surge in the popularity of generative AI has set the stage for transformative changes in forecasting. Generative AI will influence forecasting by:

  1. Automatic code generation: Large language models (LLMs) will facilitate swift and efficient code writing for developers while providing users with ready-to-use templates or even generating complete code solutions tailored to their specific forecasting needs.
  2. Natural language processing interfaces: LLMs will be integrated into forecasting systems, offering friendly and interactive natural language processing interfaces. Users will easily provide insights and receive feedback or suggestions based on the problem at hand.
  3. Enhanced interpretability: LLMs enhance interpretability and trust in forecasts by generating concise explanations or summaries of the underlying forecasting models and highlighting the key features driving the predictions.

As we step into this new era of forecasting, driven by technological advancements and the integration of generative AI, the future is promising. Accurate, adaptable and user-friendly forecasting will help organizations thrive no matter the economic conditions and pave the way for sustainable growth and resilience.

For more information about the future of forecasting, you can read the original articles published by Spiros Potamitis, Michele Trovero, and Joe Katz in Foresight Issue 71 and made available to our readers here with the permission of Foresight.

Get a glimpse into the future of forecasting software and see how generative AI will affect the future.


About Author

Spiros Potamitis

Senior Data Scientist and Global Product Marketing Manager, SAS Forecasting and Optimization

Spiros Potamitis is a Senior Data Scientist and a Global Product Marketing Manager of Forecasting and Optimization at SAS. He has extensive experience in the development and implementation of advanced analytics solutions across different industries and provides subject matter expertise in the areas of Forecasting, Machine Learning and AI. Prior of joining SAS, Spiros has worked and led advanced analytics teams in various sectors such as Credit Risk, Customer Insights and CRM.”

Leave A Reply

Back to Top