1. NCCU Academic Hub
  2. 學術產出
  3. College of Social Science
  4. Periodical Articles
  5. Item

學術產出-Periodical Articles

Article View/Open

Publication Export

Google ScholarTM

政大圖書館

Citation Infomation

題名 Predicting the failures of prediction markets: A procedure of decision making using classification models
作者 Tai, Chung-Ching
Lin, Hung-Wen
Chie, Bin-Tzong
童振源
Chen-YuanTung
貢獻者 國家發展研究所
關鍵詞 Combining forecasts; Support vector machine; Decision trees; Principal component analysis; Discriminant analysis; Imbalanced data; Oversampling; SMOTE
日期 2018-06
上傳時間 24-Jul-2018 17:27:37 (UTC+8)
摘要 Prediction markets have been an important source of information for decision makers due to their high ex post accuracies. Nevertheless, recent failures of prediction markets remind us of the importance of ex ante assessments of their prediction accuracy. This paper proposes a systematic procedure for decision makers to acquire prediction models which may be used to predict the correctness of winner-take-all markets. We commence with a set of classification models and generate combined models following various rules. We also create artificial records in the training datasets to overcome the imbalanced data issue in classification problems. These models are then empirically trained and tested with a large dataset to see which may best be used to predict the failures of prediction markets. We find that no model can universally outperform others in terms of different performance measures. Despite this, we clearly demonstrate a result of capable models for decision makers based on different decision goals.
關聯 International Journal of Forecasting
資料類型 article
DOI https://doi.org/10.1016/j.ijforecast.2018.04.003
dc.contributor 國家發展研究所
dc.creator (作者) Tai, Chung-Chingen_US
dc.creator (作者) Lin, Hung-Wenen_US
dc.creator (作者) Chie, Bin-Tzongen_US
dc.creator (作者) 童振源zh_TW
dc.creator (作者) Chen-YuanTungen_US
dc.date (日期) 2018-06
dc.date.accessioned 24-Jul-2018 17:27:37 (UTC+8)-
dc.date.available 24-Jul-2018 17:27:37 (UTC+8)-
dc.date.issued (上傳時間) 24-Jul-2018 17:27:37 (UTC+8)-
dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/118873-
dc.description.abstract (摘要) Prediction markets have been an important source of information for decision makers due to their high ex post accuracies. Nevertheless, recent failures of prediction markets remind us of the importance of ex ante assessments of their prediction accuracy. This paper proposes a systematic procedure for decision makers to acquire prediction models which may be used to predict the correctness of winner-take-all markets. We commence with a set of classification models and generate combined models following various rules. We also create artificial records in the training datasets to overcome the imbalanced data issue in classification problems. These models are then empirically trained and tested with a large dataset to see which may best be used to predict the failures of prediction markets. We find that no model can universally outperform others in terms of different performance measures. Despite this, we clearly demonstrate a result of capable models for decision makers based on different decision goals.en_US
dc.format.extent 852380 bytes-
dc.format.mimetype application/pdf-
dc.relation (關聯) International Journal of Forecasting
dc.subject (關鍵詞) Combining forecasts; Support vector machine; Decision trees; Principal component analysis; Discriminant analysis; Imbalanced data; Oversampling; SMOTEen_US
dc.title (題名) Predicting the failures of prediction markets: A procedure of decision making using classification modelsen_US
dc.type (資料類型) article
dc.identifier.doi (DOI) 10.1016/j.ijforecast.2018.04.003
dc.doi.uri (DOI) https://doi.org/10.1016/j.ijforecast.2018.04.003