Skip navigation
Title: 

Uncovering Hidden Structure in Bond Futures Trading

Authors: Chen, Fei
Figlewski, Stephen
Heisler, Jeffrey
Weigend, Andreas S.
Issue Date: Jan-1998
Publisher: Stern School of Business, New York University
Series/Report no.: IS-98-01
Abstract: This study uncovers trading styles in the transaction records of US Treasury bond futures. It uses transaction-by-transaction data from the Commodity Futures Trading Commissions' (CFTC) Computerized Trade Reconstruction (CTR) records. The data set consists of 30 million transaction - the complete US T-bond futures market for 3 years. Each transaction record consists of time (by the minute), price, volume, buy/sell, and an identifier of the specific account. We use statistical clustering techniques to group together trades that are similar. Two sets of assumptions have to be made: (1) What is a trade? We define a trade to begin when an account opens a position, and to end when its position size returns to zero. We describe each trade by several trade-specific variables (e.g., length of trade, maximum position size, opening move, long or short) and several exogenous, market-specific variables (e.g., price, volatility, trading volume). (2) What process generated the data? We assume a mixture of Gaussians. An observed trade is interpreted as a noisy realization of one of the mixture components. This paper assumes identity covariance matrices. Furthermore, each trade is fully assigned to a single cluster. We compare this approach to diagonal and to full covariance structure with probabilistic assignments. Trade profit was held back in the clustering process. It turns out that the clusters differ significantly in their profit and risk characteristics. Using conditional distributions, we summarize features of profitable trading styles and contrast them with losing strategies. We find that profitable styles tend to hold trades longer, trade at higher volatility, and trade earlier in the contracts. We also show how some clusters uncover "technical" traders. Using the information about the individual accounts, the assignments of accounts to clusters are described by entropy, and the transitions of a given account through clusters is modeled by a first order Markov model.
URI: http://hdl.handle.net/2451/14289
Appears in Collections:IOMS: Information Systems Working Papers

Files in This Item:
File Description SizeFormat 
IS-98-01.pdf14.86 MBAdobe PDFView/Open


Items in FDA are protected by copyright, with all rights reserved, unless otherwise indicated.