- Joined
- 11/3/11
- Messages
- 1
- Points
- 11
Hi, everyone.
I am a newbie in financial investment and risk management research field, only having engineering background.
Now I am exploring a research topic on hedging commodity spot price risk with futures. I try to apply approximate dynamic programming to solve a Markov Decision Optimization problem. Since approximate dynamic program is a sample path based algorithm. I need to model the commodity price.
I want to use neural network regression approach to model the commodity price, however, I found that in most cases, people adopted linear models, like Schwartz two factor model, etc..
I wonder if it is appropriate for me to use the neural network to model the commodity price and generate sample paths.
Thank you very much for reading this through and leave your advices!
I am a newbie in financial investment and risk management research field, only having engineering background.
Now I am exploring a research topic on hedging commodity spot price risk with futures. I try to apply approximate dynamic programming to solve a Markov Decision Optimization problem. Since approximate dynamic program is a sample path based algorithm. I need to model the commodity price.
I want to use neural network regression approach to model the commodity price, however, I found that in most cases, people adopted linear models, like Schwartz two factor model, etc..
I wonder if it is appropriate for me to use the neural network to model the commodity price and generate sample paths.
Thank you very much for reading this through and leave your advices!