In the rapidly evolving landscape of financial planning and analysis, Artificial Intelligence (AI) and Machine Learning (ML) have emerged as invaluable tools. Watch our webinar, where we delve into the intricacies of AI/ML within Workday Adaptive Planning and its new Intelligent Planning module, shedding light on its application in revenue forecasting and the integration of external data sources as well as walking through some real-world examples.
Understanding Intelligent Planning in Workday Adaptive Planning
Intelligent Planning is a module in Workday Planning that uses Artificial Intelligence (AI) and Machine
Learning (ML) to create more accurate, predictive plans. Within Intelligent Planning, Machine Learning is used to drive predictive forecasts using one of two open-source algorithms (Prophet or N-BEATS) while offering external data (e.g. weather, CPI, population growth) as a possible variable. Prophet and N-BEATS are popular time series forecasting algorithms that use different methodologies when creating predictions. Prophet uses seasonality of actuals AND can incorporate external data such as weather, CPI, population growth, inflation, etc, while N-BEATS uses patterns and trends found within your actuals. Here are a few use cases:
| Prophet – Revenue Forecast | N- BEATS – Revenue Forecast |
| Predicting Monthly Sales Revenue for an E- commerce Platform | Long-Term Revenue Forecasting for a Subscription-based Service |
| An e-commerce company wants to forecast its monthly sales revenue to optimize inventory and marketing strategies. Prophet can be employed to capture seasonality, trends, and potential impact of promotions. | A subscription-based service wants to forecast its revenue for the next several years. N- BEATS, with its ability to capture complex patterns and long-term dependencies can be applied for more extended forecasting periods. |
| Utilizing historical sales data, incorporating seasonality factors (e.g., holiday sales peaks), and adjusting for potential external factors influencing revenue | Training N-BEATS on historical subscription data, considering factors like user growth, retention rates, and external market trends |
| Prophet – Expense Forecast | N-BEATS – Expense Forecast |
| Monthly Operating Expenses Forecast for a Manufacturing Company | Variable Expense Forecasting for a Tech Startup |
| A manufacturing company aims to forecast its monthly operating expenses to manage cash flow efficiently. Prophet can help capture regular monthly patterns and potential one-time expense events. | A startup in the technology sector wants to forecast its variable expenses, which may vary significantly based on project requirements. N- BEATS can capture the variability and adapt to changing expense patterns. |
| Incorporating historical expense data, identifying recurring monthly expenses, and accounting for known future expenses or events | Training N-BEATS on historical expense data, considering factors like project timelines, hiring patterns, and technology development cycles |
Key Takeaways:
- Enhancing Baseline Forecast Accuracy:
- Machine learning’s capability to analyze large datasets and identify complex patterns is key to finding new insights into data. These additional insights showcase AI/ML’s role in improving baseline forecast accuracy.
- Handling Complex Relationships:
- ML algorithms can unveil non-linear patterns and dependencies in data, ensuring the capture of intricate interactions often overlooked by simpler models.
- Proactive Response to Trends:
- AI’s early detection of trends enables businesses to proactively respond to market changes, providing a competitive edge.
- Continuous Improvement:
- ML models can be refined over time with more data, leading to continuous improvement in reliability and accuracy.
The webinar showcases the transformative potential of AI/ML within Workday Adaptive Planning, especially in the realm of revenue forecasting. As organizations seek more informed and strategic decision-making processes, the integration of AI technologies proves to be a game-changer in the financial planning landscape.