Time Series Modelling with Neural Networks
The main objective of time series analysis is to provide mathematical models that offer a plausible description for a sample of data indexed by time. Time series modelling may be applied in many different fields. In finance, it is used for explaining the evolution of asset returns. In actuarial sciences, it may be used for forecasting the number of claims caused by natural phenomenons or for claims reserving.
- Dietz S (2011) Autoregressive neural network processes: univariate, multivariate and cointegrated models with application to the German automobile industry. Ph.D. Dissertation, University of PassauGoogle Scholar
- Gers FA, Schmidhuber J, Cummins F (1999) Learning to forget: continual prediction with LSTM. In: 9th international conference on artificial neural networks: ICANN’99, pp 850–855Google Scholar
- Hainaut D (2012) Pricing of an insurance bond, with stochastic seasonal effects. Bulletin Français d’actuariat 12(23):129–150Google Scholar
- Hochreiter S, Bengio Y, Frasconi P, Schmidhuber J (2001) Gradient flow in recurrent nets: the difficulty of learning long-term dependencies. In: Kremer SC, Kolen JF (eds) A field guide to dynamical recurrent neural networks. IEEE Press, PiscatawayGoogle Scholar
- Leisch F, Trapletti A, Hornik K (1999) Stationarity and stability of autoregressive neural network processes. Adv Neural Inf Proces Syst 11:267–273Google Scholar
- White H (1989) An additional hidden unit test for neglected nonlinearity in multilayer feedforward networks. In: Proceedings of the international joint conference on neural networks, Washington, vol 2, pp 90–131Google Scholar