World Models applied to Finance
Ahmet Ozkan Demir, Kwok Wai Ma, Nasim Dehghan Hardoroudi, Amey Kaloti
World Models is a concept in deep learning that aims to develop models capable of understanding and interacting with complex environments, such as video games or simulated worlds, combining techniques from reinforcement and genarative learning. The idea behind World Models is to create an internal representation of the environment, which can then be used for planning and decision-making. The concept was first introduced by Ha and Schmidhuber ( https://arxiv.org/abs/1803.10122 ). The goal of this project to apply this model to a financial setting, like Market Prediction, Portfolio Optimization, Risk Management etc. Feel free to join if you find this project interesting.