Enhanced Data-Driven Product Development via Gradient Based Optimization and Conformalized Monte Carlo Dropout Uncertainty Estimation
This work addresses data-driven product development for industries needing multi-property optimization, offering an incremental improvement in uncertainty estimation.
The paper tackled the problem of optimizing product designs by training neural networks on past data and using gradient descent to find optimal specifications, while introducing a novel uncertainty estimation method that provides coverage guarantees without retraining. The results showed state-of-the-art performance on five real-world datasets with adaptive prediction intervals.
Data-Driven Product Development (DDPD) leverages data to learn the relationship between product design specifications and resulting properties. To discover improved designs, we train a neural network on past experiments and apply Projected Gradient Descent to identify optimal input features that maximize performance. Since many products require simultaneous optimization of multiple correlated properties, our framework employs joint neural networks to capture interdependencies among targets. Furthermore, we integrate uncertainty estimation via \emph{Conformalised Monte Carlo Dropout} (ConfMC), a novel method combining Nested Conformal Prediction with Monte Carlo dropout to provide model-agnostic, finite-sample coverage guarantees under data exchangeability. Extensive experiments on five real-world datasets show that our method matches state-of-the-art performance while offering adaptive, non-uniform prediction intervals and eliminating the need for retraining when adjusting coverage levels.