Neural and Time-Series Approaches for Pricing Weather Derivatives: Performance and Regime Adaptation Using Satellite Data

TL;DR

This paper compares neural network and time-series models for pricing weather derivatives, demonstrating that neural networks improve accuracy and adapt to seasonal regimes using satellite data, with implications for valuation shifts.

Contribution

Introduces a regime-adaptive CNN approach for weather derivative pricing, capturing seasonal heterogeneity and outperforming traditional models and industry standards.

Findings

Neural network reduces out-of-sample MSE compared to time-series models.

CNN adaptively learns season-specific parameters for precipitation.

Model choice significantly impacts weather derivative valuations.

Abstract

This paper studies pricing of weather-derivative (WD) contracts on temperature and precipitation. For temperature-linked strangles in Toronto and Chicago, we benchmark a harmonic-regression/ARMA model against a feed-forward neural network (NN), finding that the NN reduces out-of-sample mean-squared error (MSE) and materially shifts December fair values relative to both the time-series model and the industry-standard Historic Burn Approach (HBA). For precipitation, we employ a compound Poisson--Gamma framework: shape and scale parameters are estimated via maximum likelihood estimation (MLE) and via a convolutional neural network (CNN) trained on 30-day rainfall sequences spanning multiple seasons. The CNN adaptively learns season-specific $(\alpha,\beta)$ mappings, thereby capturing heterogeneity across regimes that static i.i.d.\ fits miss. At valuation, we assume days are i.i.d.\ $\Gamma(\hat{\alpha},\hat{\beta})$ within each regime and apply a mean-count approximation (replacing the Poisson count by its mean ($n\hat{\lambda}$) to derive closed-form strangle prices. Exploratory analysis of 1981--2023 NASA POWER data confirms pronounced seasonal heterogeneity in $(\alpha,\beta)$ between summer and winter, demonstrating that static global fits are inadequate. Back-testing on Toronto and Chicago grids shows that our regime-adaptive CNN yields competitive valuations and underscores how model choice can shift strangle prices. Payoffs are evaluated analytically when possible and by simulation elsewhere, enabling a like-for-like comparison of forecasting and valuation methods.