Information Technology Reference
In-Depth Information
5.2
ATOM Reality-Check
In this section, we report a series of tests conducted to check whether ATOM can gen-
erate financial dynamics in line with the ones of the Euronext-NYSE stock-exchange
or not. The first series of test is devoted to the ability of ATOM at generating unbiased
prices when it deals with a real-world order-flow.
Figure 5(a) and Figure 5(b) reports results of the first reality-check (top Figures
report results produced with the ATOM data, bottom Figures being those based on
Euronext-NYSE data). We ran ATOM with a Hollow Agent reading the entire set
of 83616 orders concerning the French blue-chip France-Telecom (FTE) recorded on
June 26th 2008 between H9.02'.14”.813”' and H17.24'.59”.917”'. As mentioned previ-
ously, handling time in simulations is particularly complex and may lead to unsolvable
dilemma. We cannot guarantee an exact matching of waiting times but rather a coher-
ent distribution of these values delivered by the simulator engine with regard to the
observed waiting times.
800
1600
2400
3200
4000
4800
5600
6400
7200
8000
8800
9600
10400
800
1600
2400
3200
4000
4800
5600
6400
7200
8000
8800
9600
10400
Simulated Time
Simulated Time
10:00
12:00
14:00
16:00
10:00
12:00
14:00
16:00
Physical Time
Physical Time
(a) Prices: ATOM vs. Euronext-NYSE.
(b) Volumes: ATOM vs. Euronext-NYSE.
Fig. 5.
Results of the ”Reality Check” procedure
Notice that ATOM performs rather decently in satisfying the first reality check
procedure.
5.3
Stylized Facts
The second subset of tests focuses on ATOM ability to generate realistic artificial prices
when populated with artificial agents. We ran a series of simulations to verify if ATOM
can generate major stylized facts that are usually reported in the literature (see for exam-
ple [27]). For the sake of simplicity and space-saving, we only report in a pictorial form
of the classical departure from Normality of asset returns at the intraday level (Figures
