Research Structure

國

立立 政 治 大

㈻㊫學

•‧

N a tio na

l C h engchi U ni ve rs it y

Marriage of social network analysis with investing behavior: We explore how similarity between investors and companies affect investing behavior through social network analysis. Also, our work is amongst the first to use data from CrunchBase as a social network for research purposes.

1.2.3 Providing general rules of thumb for companies seeking investment

Our recommendations for companies seeking investment are based on intuitive and common similarity measures to show where companies can find potential investors within their social network. Using these general rules, we hope to increase companies’ chances of getting funded from investors.

1.3 Research Structure

The thesis is structured based on ideas summarized by Alan, Salvatore, Jinsoo, and Sudha on 2004 et al in 2004 as shown in Figure 1.1:

•‧

國

立立 政 治 大

㈻㊫學

•‧

N a tio na

l C h engchi U ni ve rs it y

For any IT systems to be useful, it must take into account of various factors, ranging from stakeholders, organizational structure, available IT systems architecture and strategy required to implement this system. In this research, we focus on reducing the market inefficiency cost of getting investors meet companies and vice versa; an IT artifact is a reasonable solution for this problem because an IT artifact cannot only scale up, but also scale down: companies, whether large or small will require external capital at some time or another. Large companies generally have little issues with securing external investments, but smaller companies such as startups not only have limited financial resources, they have limited manpower to seek external funding. Having an IT artifact, which allows access 24/7, provides a cheaper solution for companies, large and small.

In addition, investors are no longer limited to their own geographic location; their social network which may span across geographic regions are likely sources of investees; an IT artifact will allow them effective access to potential investees. The same could be said for companies.

Lastly, there are available algorithms and open source software to provide the required IT implementation and recommendations; which points to the fact that the IT artifact can be implemented with current technologies.

Going deeper into this research structure, we need a research framework for not only the implementation of this IT artifact, but also provide strong theoretical foundations for this system:

•‧

國

立立 政 治 大

㈻㊫學

•‧

N a tio na

l C h engchi U ni ve rs it y

Figure 1.2: Information Systems Research Framework

The research framework is also inspired by Alan, Salvatore, Jinsoo, and Sudha (2004): in chapter 2 we first cover related literature pertaining to our research topic and related state of art. In chapter 3, we briefly go through how this research work is part of a larger picture known as Prosperity Taiwan. In Chapter 4, we focus on theoretical foundations on how we intend to solve the problem of predicting investments by modeling it based on the classic link prediction problem, where given a network at time0, we attempt to predict new links created at time1 where time1 represents a time in the future. In our network, we have 2 node types: Investor and Company. Next in chapter 5, we perform experiments and evaluate the effectiveness of our methods using classic metrics for machine learning problems: Area Under Curve, True Positive Rate and False Positive Rate. To further strengthen the evaluation aspect of this research, we verify our model using a different subset of our database; this is performed in chapter 6.

•‧

國

立立 政 治 大

㈻㊫學

•‧

N a tio na

l C h engchi U ni ve rs it y

varied performance. A walkthrough of the result IT artifact is shown in chapter 8. Finally, we summarize and conclude this research work with various possibilities of extending this research work.

•‧

We have two parts for related works since our research focuses on the use of social network analysis on investment behavior: previous research on investment behaviors and previous research on social network analysis.

2.2 Related Research on Investment Behaviors

Prior studies on investment behaviors can be categorized into 6 categories based on the type of factors that drive investment behaviors.

1. Personal Opinions. Doran, Peterson and Wright (Doran et al., 2010) studied the role of personal opinions of finance professors on the efficiency of the stock market in the United States and found out that personal opinions do not affect investment behaviors. Rather, investment behaviors found in financial professors were largely driven by the same behavioral factor as amateur investors.

2. Investment Experience. Gorat et al., 2011 analyzed the differences in the investment behaviors of experienced and novice private equity firms and found out that novice firms tend to invest more slowly than experienced funds but the size and value of the funding size of novice firms tend to be larger.

3. Geographic Identities. Grinblatt et al., 2000 discovered that investment behaviors can be determined by the investors geographic identity: foreign investors in Finland tend to purchase past winning stocks and sell past losers. On the other hand, domestic investors sell past winning stocks and purchase losing stocks.

4. Online versus Offline Communities. Tan et al., in 2011 explored the roles played by online and offline communities and discovered that offline communities are more influential over investing behaviors. This is expected since offline communities often mean that interaction are offline and hence more likely in person, thus increasing the level of influence.

5. Psychology. Bakker et al., in 2010 on the other hand investigated into psychological factors that impact market evaluation and found out that trust and social influence affects the stability of investment markets.

6. Genetics. Barnea et al in 2010 investigated the relationship between genetics and investment behavior by studying the investment behaviors of identical and fraternal twins. They discovered that “a genetic factor” explains up to a third of twins investing behavior, though not long lasting.