Information Technology Reference
In-Depth Information
Order probability regime R
2
− low − 1189tac4
Order probability regime R
3
− low − 1189tac4
S
1
1
0.9
0.9
0.8
0.8
0.7
0.7
B
0.6
0.6
0.5
0.5
0.4
0.4
O
0.3
0.3
0.2
0.2
0.1
0.1
0
0
0
20
40
60
80
100
120
140
160
180
200
220
0
0.2
0.4
0.6
0.8
1
1.2
0
0.2
0.4
0.6
0.8
1
1.2
Time in Days
Normalized Price
Normalized Price
Fig. 6.
Game 1189@tac4 (Final TAC SCM 04) - Regimes over time for the low market computed
online every day (left), probability of receiving an order by normalized price for a balanced
situation (
R
2
indicated by
B
) (middle) and for a scarcity situation (
R
3
indicated by
S
) (right).
at other times when supply is low. These probabilities are computed from past game
data for each regime.
Eventual errors in regime identification can be corrected every 20 days when the
agent receives a market report which includes the mean price of each of the computer
types sold since the last market report. At that point, if needed, the agent can correct its
current regime identification.
B
O
B
B
O B
S
O
1
1
10000
FG
np
Offer/Demand
0
0
0
0
0
0
50
50
50
100
100
100
150
150
150
200
200
200
Day
Fig. 7.
Game 1189@tac4 (Final TAC SCM 04) - Relationships between regimes and normalized
prices in the low market. On the left axis, we show the available finished goods inventory of
all agents and the ratio of offer to demand (which ranges from 0 to 4.5), which is scaled to fit
between the minimum and maximum values of the finished goods inventory. On the right axis we
show the normalized prices. The dominant regimes are labeled along the top.
