Financial Applications: Stock Markets

Abstract

The integration of computer science, computer technology, and finance has given rise to the field known as computational finance. Depending on its involvement in economic theory and its contribution to economic theory, computational finance can be divided into financial engineering and agent‐based computational finance. Financial engineering can be defined as the application of computational tools or algorithms to tackle some already existing financial optimization problems, such as forecasting, investment, portfolios, trading, and pricing. These applications usually do not challenge the fundamental principles (assumptions or axioms) from which the optimization problems are derived. They simply take advantage of the increasing computational power to address great technical difficulties inherent in financial optimization, such as nonlinearities and high dimensionality. Compared to financial engineering, agent‐based computational finance has a more general goal. It questions the foundations up on which mainstream economics and finance are built, and it reexamines some missing elements, which were absent mainly due to the limited computational resources. Then, by bringing back these elements, agent‐based computational finance attempts to provide us with a better understanding of the financial market dynamics.

Testing the Dinosaur Hypothesis under different GP algorithms

“…MA As we can see from the new syntax at Figure 2, the Variable symbol has been replaced by the VarConstructor 3 As we have mentioned, each GDT makes recommendations of buy (1) or not-to-buy (0). The former denotes a positive signal and the latter a negative.…”

“…Based on these observations, Chen [3] suggested a new hypothesis, called the Dinosaur Hypothesis. The DH states that the market behaviour never settles down and that the population of predictors continually co-evolves with this market.…”

Emergent Complexity in Agent-Based Computational Economics

“…In , we provide a brief review of the complex system which gained its popularity in the 1980s in both physics and economics. Its extensive applications to agent‐based economic and financial models in the 1990s has generated a major class of ACE models called the N ‐type models (Chen, 2008). This complex system, however, is composed of only simple and homogeneous agents , which means that this system is not far away from the particle system in physics, and in many regards cannot accommodate the needs of the integrated framework mentioned above.…”