Modeling market fluctuations under investor sentiment with a Hawkes-Contact process

Abstract

We present a new Hawkes-Contact model that combines a Hawkes process and a finite range contact process in order to model the stock price movements, especially under the impact of news and other information flows that could lead to contagious effects. To fully capture the underlying price process, we take the Hawkes process to track the full pathway of historical prices on their future movements and the contact process to capture the impact from news/investment sentiment. We compare this full model to a univariate Hawkes process that works as a benchmark model through analyzing their statistical properties using both simulated returns and the real five-minute returns of the crude oil index (Wind CZCE-TA). The statistical properties include probability density function (PDF), complementary cumulative distribution function (CCDF), Lempel-Ziv Complex (LZC). Our results show that the real returns' distribution is often far from normal but the simulated returns through the Hawkes or Hawke-contact model can achieve close fit to the real returns and exhibit similar statistical properties. More importantly, the Hawkes-Contact model performs better than the simple Hawkes model in capturing characteristics in the return movements, which indicates that the price evolution is also driven by the news announcements and sentiment created after them.

Review and Assessment of Digital Twin–Oriented Social Network Simulators

“…As is shown in Table 3, most SNSs focus on static networks with no attributes, which are categorised as G1/G2a models and characterised with the lowest level of complexity in each dimension. They generate networks based on predetermined network statistics and connection principles about topology [4], [5], [13], [15]- [19], [23]- [36], [41], [53]- [57]. Some other SNSs, with higher level of structural complexity, incorporate node attributes [7], [37]- [39], edge attributes [22], [52] or both of them [43]- [45] into the generation process of static networks.…”

Toward Digital Twin Oriented Modeling of Complex Networked Systems and Their Dynamics: A Comprehensive Survey

“…Another type of simulation-based networks, the principlebased simulations, are built according to different connection principles like homophily [148], [149], triadic structure [149], geographic proximity [152], [159]. These networks have typically higher degrees of temporal and dynamics complexity than statistics-based network simulations as they self-evolve with highly autonomous and interpretable edge formation process and generate temporal networked information.…”

“…As is shown in Table 3, most SNSs focus on static networks with no attributes, which G1/G2a [6], [20], [80], [24], [2], [3], [85], [55], [71], [73], [86], [84], [75][77], [78], [31], [40], [27], [68], [21], [1], [9], [83], [59], [33], [39], [10], [32], [57], [11], [30], [23], [53], [36], [5], [74] [18], [54] [49], [52], [79], [70] G2b/G3 [34], [69], [87], [51] [4], [7], [8], [72], [28], [76] [4],…”

“…[29], [43], [22] are categorised as G1/G2a models and characterised with the lowest level of complexity in each dimension. They generate networks based on predetermined network statistics and connection principles about topology [1,2,3,6,9,10,11,20,23,24,30,31,32,33,39,55,57,59,71,73,75,77,78,80,83,84,85,86]. Some other SNSs, with higher level of structural complexity, incorporate node attributes [5,36,53,74], edge attributes [18,54] or both of them [49,52,79] into the generation process of static networks.…”

Towards Digital Twin Oriented Modelling of Complex Networked Systems and Their Dynamics: A Comprehensive Survey

“…Another type of simulation-based networks, the principlebased simulations, are built according to different connection principles like homophily [142], [143], triadic structure [143], geographic proximity [146], [153]. These networks have typically higher degrees of temporal and dynamics complexity than statistics-based network simulations as they self-evolve with highly autonomous and interpretable edge formation process and generate temporal networked information.…”