How This Workflow Works
This workflow merges financial and ESG data, trains and applies a machine learning regression model to predict future growth and estimates the probability of slowdown. The trained model is then applied to new financial data, with results presented through interactive visualizations in a Data App that also enables users to simulate ESG adjustments and assess their impact on future growth.
Key Features:
- Combine financial and ESG data for holistic analysis
- Train and apply a machine learning model to forecast growth
- Estimate the probability of growth slowdown
- Identify key financial and ESG drivers of performance
- Simulate ESG adjustments and explore results interactively
Step-by-step:
1. Integrate Financial and ESG Factors:
Merge company financial metrics with ESG scores into a unified dataset that captures both traditional and sustainability-related factors.
2. Train and Apply a Predictive Model:
Use historical data to train a Random Forest regression model and generate forward-looking growth predictions for new data.
3. Evaluate Drivers and Estimate Slowdown Risk:
Evaluate which features are most important to forecast growth, and calculate the probability that predicted growth falls below a defined threshold, quantifying growth slowdown risk.
4. Forecast Growth on New Data and Simulate ESG Scenarios in the Data App:
Apply the trained model to new financial data and generate forecasts for upcoming years. Explore the results through interactive visualizations in a Data App and dynamically adjust ESG scores to assess their impact on growth forecasts.