Information Technology Reference
In-Depth Information
The long term objective of our work is to show how knowledge of current and antic-
ipated market conditions enables an agent to make better decisions. While this type of
prediction about the economic environment is commonly used at the macro economic
level, such predictions are rarely done for a micro economic environment.
2
Economic Regime Identification
To give an intuition of how prices for the same type of computer change during the
game, we show in Figure 1 the probability of receiving an order for a given offer price
for computers of type 1 during one of the games played in the finals of TAC SCM 2004.
We can see how the slope of the curve and its position change over time. According
to economic theory high prices and a steep slope correspond to a situation of scarcity,
where price elasticity is small, while a less steep slope corresponds to a balanced market
where the range of prices is larger.
1
0.9
0.8
0.7
0.6
1−20
21−40
41−60
61−80
81−100
101−120
121−140
141−160
161−180
181−200
201−220
0.5
0.4
0.3
0.2
0.1
0
0
0.2
0.4
0.6
0.8
1
1.2
Normalized Price
Fig. 1. Game 1189@tac4 (Final TAC SCM 04) - Probability of order for computer type 1 by
offer price. The plot shows the curves every 20 days during the game.
Clearly market conditions change during the game, and this should affect the strategy
of the agent. When there is scarcity, prices are higher, so the agent should price aggres-
sively. In balanced situations, prices are lower and have more spread, so the agent has
a range of options for maximizing expected profit. In over-supply situations prices are
lower. The agent should primarily control costs, and therefore either do pricing based
on costs, or wait for better market conditions.
Since supply and demand in TAC SCM change in each of the market segments (low,
medium, and high computer prices) independently of the other segments, our consider-
ations are to be applied to each individual market segment.
 
Search WWH ::




Custom Search