本研究旨在建構基於委託量之個股經紀商資訊流網絡(volume based broker information network)，探討網絡結構與市場特徵之關係，並利用機器學習分群投資人類型及預測市場短期價格走勢。本文是首篇利用委託量來建構資訊流網絡，並有效的利用網絡參數來分群投資人的研究。
本研究透過網絡 (network) 之分析方法，透過網絡參數變化，可以讓我們了解市場資訊的變化與流動。而網絡中心性與模組化程度可以直接衡量資訊不對稱與意見分歧或從眾行為，甚至領先傳統的資訊風險衡量方式，透過分析網絡參數，我們能夠了解投資者行為與市場特徵間的關係。
Admati 與Pfledierer (1998)首次將投資人分為三類，他們指出資訊投資人與流動性投資人的交易會使股票成交量聚集，Delong et al.(1990a,1990b)也提出雜訊交易者與理性投機者對於股市資訊與波動性的影響，所以如何有效分類投資人類型是市場相關實證研究的一大課題;而本研究使用機器學習，透過輸入網絡參數資料，可以有效的分類出資訊投資人以及雜訊投資人以及提升短期股價趨勢的預測能力。
除此以外，過去網絡分析的建構方式通常是以時間為單位來建構，本研究則將交易量視為時間單位，當累積到某特定交易量時即建構一個網絡，以此方式建構之每個網絡會有固定的資訊含量，因此，所計算出的網絡參數較有穩定性，且較能捕捉到市場上資訊的流動。以此方法所建構之網絡可以較過去文獻研究更深入的解讀目前市場上資訊如何流動，並進一步判斷與價格走勢的影響。

In this study we construct volume-based broker information network and explore the relationship between network topologies and market quality; furthermore, the study uses machine learning to classify investor types and predict short-term price movements in the market. This study is the first use order volume to construct the information network and effectively grouping investors by network topology and machine learning.
This study uses social network analysis methods to extract network topologies parameters such as centrality and modularity from the network. Centrality and modularity provides useful information regarding the information asymmetry and herding propensity of the network. As network topologies directly reflect the dynamics of information transmission structure among nodes (investors), they may be a quicker or better estimate of information risk.
Admati and Pfledierer (1998) first posit that there are three types of investors, informed traders, discretionary and non-discretionary liquidity trader. Delong et al. (1990a, 1990b) point out the effect of noise traders and informed traders on market volatility. The proportion of different investors can affect security price risk and even pricing. Therefore, how to classify investors effectively is a major issue in financial market research. This study attempts to use machine learning to help us classify investor type and predict stock price trends while incorporating network topologies into the algorithm.
In addition, previous network study usually constructs the network in a time-based manner, for example, a daily network. In this study, the network is constructed based on volume. As each network has an equal volume or thickness of information content, the network parameters are more stable, and provide better measure of the flow of information in the market.

論文審定書 i
摘要 ii
ABSTRACT iii
CONTENTS iv
LIST OF FIGURES vii
LIST OF TABLES viii
Chapter 1 INTRODUCTION 1
1.1 Background Information 1
1.2 Research Purpose 2
1.3 Research Contribution 3
Chapter 2 LITERATURE REVIEW 4
Chapter 3 METHODOLOGY 7
3.1 Data Description 7
3.2 Network Analysis 8
3.2.1 Volume Bucketing 8
3.2.2 Volume Based Broker Information Network 9
3.2.3 Network Parameters 10
3.3 Econometric Model 14
3.3.1 Network Topology and Market Quality 14
3.3.2 Investor Centrality and Profitability 14
3.4 Machine Learning 15
3.4.1 Forecast Short-Term Price Trends 15
3.4.2 Group Investor Types 16
Chapter 4 EMPIRICAL RESULTS 17
4.1 Descriptive Statistics 17
4.1.1 Stock and Volume Bucketing 17
4.1.2 Volume-Based Broker Information Network 19
4.1.3 Time Based Broker Network 26
4.2 Network Topology and Market Quality 27
4.2.1 Volume-Based Network v.s. Time-Based Network 27
4.2.2 Volume-Based Network and Market Quality 28
4.3 Forecasting Short-term Price Trends 33
4.3.1 Comparison of predictive power 33
4.3.2 Important Variables Analysis 34
4.4 Grouping Investors 37
4.4.1 Investor Centrality and Profitability 38
4.4.2 Grouping Investors by Machine Learning 40
4.4.3 Follow with Informed Traders 42
Chapter 5 CONCLUSION 44
5.1 Conclusion 44
5.2 Future Work 45
REFERENCES 46
APPENDIX 49

Amihud, Y. (2002). Illiquidity and stock returns: cross-section and time-series effects. Journal of Financial Markets, 5(1), 31-56.
Anat R. Admati , Paul C. Pfleiderer (1988), Selling and Trading on Information in Financial Markets, American Economic Review. 1988, Vol. 78, Pages 96–103
Baker, M. and Wurgler, J. (2006), ‘Investor Sentiment and the Cross-Section of Stock Returns’, The Journal of Finance, Vol. 4
Barigozzi, M., Fagiolo, G., & Garlaschelli, D. (2010). Multinetwork of international trade: A commodity-specific analysis. Physical Review E, 81(4), 046104.
Boss, M., Elsinger, H., Summer, M., & Thurner 4, S. (2004). Network topology of the interbank market. Quantitative finance, 4(6), 677-684.
Chan, K., & Fong, W. M. (2000). Trade size, order imbalance, and the volatility–volume relation. Journal of Financial Economics, 57(2), 247-273.
Chen, L., Qin, L., & Zhu, H. (2015). Opinion divergence, unexpected trading volume and stock returns: Evidence from China. International Review of Economics & Finance, 36, 119-127.
Chordia, T., Roll, R., & Subrahmanyam, A. (2002). Order imbalance, liquidity, and market returns. Journal of Financial economics, 65(1), 111-130.
Cohen-Cole, E., Kirilenko, A., & Patacchini, E. (2014). Trading networks and liquidity provision. Journal of Financial Economics, 113(2), 235-251.
Ding, R., & Hou, W. (2015). Retail investor attention and stock liquidity. Journal of International Financial Markets, Institutions and Money, 37, 12-26.
Easley, D., & O'hara, M. (2004). Information and the cost of capital. The journal of finance, 59(4), 1553-1583.
Easley, D., Kiefer, N. M., O'hara, M., & Paperman, J. B. (1996). Liquidity, information, and infrequently traded stocks. The Journal of Finance, 51(4), 1405-1436.
Easley, D., López de Prado, M. M., & O'Hara, M. (2012). Flow toxicity and liquidity in a high-frequency world. The Review of Financial Studies, 25(5), 1457-1493.
Glosten, L. R., & Milgrom, P. R. (1985). Bid, ask and transaction prices in a specialist market with heterogeneously informed traders. Journal of financial economics, 14(1), 71-100.
Grossman, S. J., & Stiglitz, J. E. (1980). On the impossibility of informationally efficient markets. The American economic review, 70(3), 393-408.
Hein, O., Schwind, M., & Spiwoks, M. (2012). Network centrality and stock market volatility: The impact of communication topologies on prices. Journal of Finance and Investment Analysis, 1(1), 199-232.
Hellwig, M. F. (1980). On the aggregation of information in competitive markets. Journal of economic theory, 22(3), 477-498.
Hellwig, M. F. (1980). On the aggregation of information in competitive markets. Journal of economic theory, 22(3), 477-498.
Hochberg, Y. V., Ljungqvist, A., & Lu, Y. (2007). Whom you know matters: Venture capital networks and investment performance. The Journal of Finance, 62(1), 251-301.
Jiang, Z. Q. and Zhou, W. X. (2010), ‘Complex stock trading network among investors’, Physica A, Vol.389, Issue 21, 4929-4941
Kuzubaş, T. U., Ömercikoğlu, I. and Saltoğlu, B. (2014), ‘Network centrality measures and systemic risk: An application to the Turkish’, Physica A, Vol. 405, 203-215
Leo, B. (2001), ‘Random Forests’, Machine Learning, Vol. 45, Issue 1, 5-32
Malmendier, U., Shanthikumar, D., Ozsoylev, H. N., Walden, J., Yavuz, M. D., Bildik, R., ... & Georgarakos, D. (2014). Review of Financial Studies.
Manela, A. (2014). The value of diffusing information. Journal of Financial Economics, 111(1), 181-199.
Ozsoylev, H. N., & Walden, J. (2011). Asset pricing in large information networks. Journal of Economic Theory, 146(6), 2252-2280.
Pareek, A. (2012). Information networks: Implications for mutual fund trading behavior and stock returns. Paper presented at the AFA 2010 Atlanta Meetings Paper.
Serrano, M. A., & Boguná, M. (2003). Topology of the world trade web. Physical Review E, 68(1), 015101.
Suominen, M. (2001). Trading volume and information revelation in stock market. Journal of Financial and Quantitative Analysis, 36(4), 545-565.
Teng, C. Y., Gong, L., Eecs, A. L., Brunetti, C., & Adamic, L. (2012, June). Coevolution of network structure and content. In Proceedings of the 4th Annual ACM Web Science Conference(pp. 288-297). ACM.
Tetlock, P. C. (2010). Does public financial news resolve asymmetric information? Review of Financial Studies, 23(9), 3520-3557.
Tse, C. K., Liu, J. and Lau, F. C. M. (2010), ‘A network perspective of the stock market’, Journal of Empirical Finance, Vol. 17, pp. 659-667
Tumminello, M., Matteo, T. D., Aste, T. and Mantegna, R. N. (2007), ‘Correlation based networks of equity returns sampled at different time horizons’, The European Physical Journal B, Vol. 55
Varian, H. R. (1985). Divergence of opinion in complete markets: A note. The Journal of Finance, 40(1), 309-317.
Walden, J. (2014). Trading, profits, and volatility in a dynamic information network model. Available at SSRN 2561055.