TY - GEN
T1 - Automated strategy searches in an electronic goods market
T2 - 1st ACM Conference on Electronic Commerce, EC 1999
AU - Brooks, Christopher H.
AU - Fay, Scott
AU - Das, Rajarshi
AU - MacKie-Mason, Jeffrey K.
AU - Kephart, Jeffrey O.
AU - Durfee, Edmund H.
PY - 1999
Y1 - 1999
N2 - Markets for electronic goods provide the possibility of exploring new and more complex pricing schemes, due to the flexibility of information goods and negligible marginal cost. In this paper we compare dynamic performance across price schedules of varying complexity. We provide a monopolist producer with two machine learning methods which implement a strategy that balances exploitation to maximize current profits against exploration to improve future profits. We find that the complexity of the price schedule affects both the amount of exploration necessary and the aggregate profit received by a producer. In general, simpler price schedules are more robust and give up less profit during the learning periods even though the more complex schedules have higher long-run profits. These results hold for both learning methods, even though the relative performance of the methods is quite sensitive to differences in the smoothness of the profit landscape for different price schedules. Our results have implications for automated learning and strategic pricing in non-stationary environments, which arise when the consumer population changes, individuals change their preferences, or competing firms change their strategies.
AB - Markets for electronic goods provide the possibility of exploring new and more complex pricing schemes, due to the flexibility of information goods and negligible marginal cost. In this paper we compare dynamic performance across price schedules of varying complexity. We provide a monopolist producer with two machine learning methods which implement a strategy that balances exploitation to maximize current profits against exploration to improve future profits. We find that the complexity of the price schedule affects both the amount of exploration necessary and the aggregate profit received by a producer. In general, simpler price schedules are more robust and give up less profit during the learning periods even though the more complex schedules have higher long-run profits. These results hold for both learning methods, even though the relative performance of the methods is quite sensitive to differences in the smoothness of the profit landscape for different price schedules. Our results have implications for automated learning and strategic pricing in non-stationary environments, which arise when the consumer population changes, individuals change their preferences, or competing firms change their strategies.
UR - http://www.scopus.com/inward/record.url?scp=0011979798&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0011979798&partnerID=8YFLogxK
U2 - 10.1145/336992.337000
DO - 10.1145/336992.337000
M3 - Conference contribution
AN - SCOPUS:0011979798
SN - 1581131763
SN - 9781581131765
T3 - ACM International Conference Proceeding Series
SP - 31
EP - 40
BT - Proceedings of the 1st ACM Conference on Electronic Commerce, EC 1999
Y2 - 3 November 1999 through 5 November 1999
ER -