Acting optimally in partially observable stochastic domains
AAAI'94 Proceedings of the twelfth national conference on Artificial intelligence (vol. 2)
Markov Decision Processes: Discrete Stochastic Dynamic Programming
Markov Decision Processes: Discrete Stochastic Dynamic Programming
Time Series Prediction and Neural Networks
Journal of Intelligent and Robotic Systems
Dynamic Programming
Exact and approximate algorithms for partially observable markov decision processes
Exact and approximate algorithms for partially observable markov decision processes
Automated Planning: Theory & Practice
Automated Planning: Theory & Practice
Heuristic search value iteration for POMDPs
UAI '04 Proceedings of the 20th conference on Uncertainty in artificial intelligence
Technical analysis: the complete resource for financial market technicians
Technical analysis: the complete resource for financial market technicians
Point-based value iteration: an anytime algorithm for POMDPs
IJCAI'03 Proceedings of the 18th international joint conference on Artificial intelligence
| Hi-index | 0.00 |
Analysts and investors use Technical Analysis tools to create charts and price indicators that help them in decision making. Chart patterns and indicators are not deterministic and even analysts may have different interpretations, depending on their experience, background and emotional state. In this way, tools that allow users to formalize these concepts and study investment policies based on them can provide a more solid basis for decision making. In this paper, we present a tool we have built to formally model stock investment contexts as Partially Observable Markov Decision Processes (POMDP), so that investment policies in the stock market can be generated and simulated, taking into consideration the accuracy of Technical Analysis techniques. In our models, we assume that the trend for the future prices is part of the state at a certain time and can be "partially observed" by means of Technical Analysis techniques. Historical series are used to provide probabilities related to the accuracy of Technical Analysis techniques, which are used by an automated planning algorithm to create policies that try to maximize the profit. The tool also provides flexibility for trying and comparing different models.