Tag: feature engineering

In industries like Financial Services, Housing, and Insurance, the automated scoring of client risk can provide critical benefits. By quantifying the potential hazards for an organization, risk profiling helps organizations build sustainable long-term growth and minimizes losses in economic downturns. However, traditional client risk scoring methodologies are often not sufficient but can be augmented with machine learning-based models. Client Risk Profile Examples Popular use cases across different domains include: Which of my customers might default on loan payments? (Finance)Can a supplier deliver goods on time? (Manufacturing)Will my new tenant pay the rent on time? (Housing)What are the risks associated with a specific property or driver? (Insurance) Challenges with Traditional Risk Profiling Methods Traditionally, businesses solved these use-cases with rule-based approaches. A banker might have used a credit score and household income to determine loan eligibility. Simple rule-based logic is easy to implement but does not provide enough scalability and robustness…

New automated feature engineering tools remove the need to choose between accuracy and interpretability. Revenue and demand forecasting are among the most common use cases in data science, with abundant available data and clear business value across multiple industries. However, little agreement remains about the ‘best’ approach for building such forecasting models. New automated feature engineering tools are making that debate less relevant. Drawbacks of Traditional Forecasting Solutions Algorithms such as ARIMA (Autoregressive Integrated Moving Average), SARIMA (Seasonal Autoregressive Integrated Moving Average), or XGBoost, remain popular due to their flexibility and interpretability. In a search for superior predictive performance, practitioners have been learning and incorporating an ever-expanding catalog of AI-based neural network architectures into their forecasting. Despite often outperforming classical approaches in forecasting accuracy, neural networks are not a one-size-fits-all solution. Neural networks are mostly uninterpretable, leaving the business with limited insights into what’s driving the forecast, limiting business impact…