We introduce a new inductive bias for learning in dynamic event-based human systems. This is intended to partially address the issue of deep learning in chaotic systems. Instead of fitting the data to polynomial expansions that are expressive enough to approximate the generative functions or of inducing a universal approximator to learn the patterns and inductive bias, we only assume that the relationship between the input features and output classes changes over time, and embed this assumption through a form of dynamic contrastive learning in pre-training, where pre-training labels contain information about the class labels and time periods. We do this by extending and integrating two separate forms of contrastive learning. We note that this approach is not equivalent to inserting an extra feature into the input data that contains time period, because the input data cannot contain the label. We illustrate the approach on a recently designed learning algorithm for event-based graph time-series classification, and demonstrate its value on real-world data.

Abstract Early detection of intracountry outbreaks of violence or intercountry conflicts plays animportant role in geopolitics. Generally, it is based on the use of handcrafted countryfeatures (e.g., demographics, economics) that may serve as proxy to the event ofinterest. While such features matter, it is often their evolution over time both at thecountry level and among countries. As such, we propose to use a graph-basedapproach that allows us to capture static, structural and sequential measures. Usingwell-known data sets, we show how this approach outperforms both baseline andstate-of-the-art approaches.

While many CEOs are increasingly engaging in activism by publicly expressing their views onsocial, environmental, and political issues, other CEOs have refrained from doing so—a behaviorwe refer to as CEO inactivism. Using an experiment, we offer evidence on how CEO (in)activismimpacts investor decisions. Consistent with our theoretical predictions, we predict and find thatrelative to when a CEO expresses a social position inconsistent with investor position, investmentdecisions are more favorable when the CEO expresses a position consistent with investor positionor when the CEO does not express a position (i.e., inactivism). Additionally, CEO inactivism leadsto similar investment decisions as when the CEO expresses a position consistent with investorposition. Results also reveal that whether CEO (in)activism is prompted or unprompted does notappear to impact investor decisions. Process evidence supports our theory and helps explain theseresults. First, we find that CEO activism causes participants to focus more on the CEO and theCEO's position and less on the firm's financial performance. Second, CEO inactivism results inparticipants being more likely to project their own views onto the CEO and think that the CEOholds the same views as them. Finally, we find evidence suggesting that investors endorse theCEO's (in)activism more when the CEO either expresses a position consistent with their own ordoes not express a position. Our study contributes to the emerging literature on CEO activism, aunique form of voluntary disclosure, by providing causal evidence of (in)activism. We alsocontribute to the literature examining the impact of social media disclosure on investor decisions.Finally, our findings have practical implications for CEOs who are increasingly called on topublicly express stances on social controversies.

ABSTRACT Capital constraints require companies to prioritize among the host of sustainability issues to which they can allocate capital. In this study, we investigate the role of three important factors that can affect this prioritization process: key decision-makers, sustainability reporting models, and stakeholder communications. We investigate these factors through the lenses of economic theory (i.e., the shareholder value approach), stakeholder theory, and enlightened stakeholder theory by collecting survey evidence from 104 managers in the resource transformation sector who are involved in or familiar with their company's prioritization process. This study contributes to the literature by providing important insights into companies' internal decision-making processes regarding sustainability issue prioritization. JEL Classifications: G34; M14; M41. Data Availability: The data are available from the authors upon request.

Firms’ efforts to mitigate greenhouse gas emissions and curb climate change has recently become a significant area of concern to investors. We examine how management’s focus on mitigating its direct versus indirect emissions influences a firm’s ability to attract capital from investors, and how this ability is moderated by the firm’s corporate social responsibility (CSR) performance and adoption of an external emissions target. Using an experiment, we predict and find that investors perceive a firm with a relatively poor CSR performance record as more socially responsible, and therefore as a more attractive investment, when the firm focuses on mitigating direct versus indirect emissions. However, investors seem less concerned about the type of emissions firms mitigate when the firm has a relatively good CSR performance record. We also find that, regardless of CSR performance, adopting an external emissions target diminishes investment attractiveness when the firm focuses on mitigating indirect emissions, but not when the firm focuses on mitigating direct emissions. We discuss implications for theory and practice.

Empirical evidence suggests that ensembles with adequate levels of pairwise diversity among a set of accurate member algorithms can significantly outperform any of the individual algorithms. As a result, several diversity measures have been developed for use in optimizing ensembles. We show, however, that there is natural tension between the pairwise diversity of ensemble members and their individual accuracy. While efficient ensembles can be built with stronger forms of diversity, they also suffer in overall accuracy. On the other hand, ensembles built with weaker forms of diversity can be very accurate, but tend to be significantly more computationally expensive. We discuss these findings in light of the notion of diversity space.

ABSTRACT This article reports two experiments testing how managers' capital allocation decisions are affected by where and to whom they report corporate social responsibility (CSR) information. Drawing on accountability theory, I predict that managers allocate more money to CSR activities when that information is reported in a dedicated CSR report that is intended for all stakeholders, compared to settings where it is reported in a financial report or when the information is intended specifically for capital providers. I find support for this prediction using graduate business students (Experiment 1) as participants, but not Mechanical Turk workers (Experiment 2). However, exploratory analyses indicate that my prediction is supported in Experiment 2 among millennial participants and that this result is attributable to participant age rather than work experience or preferences for CSR. This generational difference between millennials and non-millennials is consistent with recent research suggesting millennials are particularly sensitive to accountability pressures. JEL Classifications: G31; G41.

With the popular and increasing power of the Internet these days, the effort of distributing and inventory costs of stocking various online retailing items are nearly negligible. In addition to selling popular, called "short-head", items in large quantities, online retailers, such as Amazon, offer a large number of unique items, called "long tail", with relatively small quantities sold. Retailers realize that it has high value to sell items from the long-tail category, since for users these long-tail items could meet the interest of them and surprise them simultaneously. Retailers also recognize that long-tail items can be an untapped source of revenue for a business; however, it is difficult to connect customers with long-tail items they are interested in, since they are unaware of them. Recommender systems help bridge the gap between users and long-tail items by learning user preferences and recommending appropriate items to them. In this paper, we propose a new tripartite graph recommender system, which is designed to suggest long-tail items. Compared with other graph-based recommender systems, our proposed recommendation system solves the tripartite variant problem suffered by existing approaches for having a low diversity score. A rework of the tripartite graph system is introduced, called the extended tripartite graph system, which enhances the performance of existing long-tail recommendation approaches measured by using two widely-used performance metrics: recall and diversity. Experimental results on the extended tripartite graph algorithm verify its merits and novelty.

While current state-of-the-art recommendation systems perform fairly well, they generally do better at recommending the popular subset of all products available rather than matching consumers with the vast amount of niche products in what has been termed the “Long Tail”. In their seminal work, “Challenging the Long Tail Recommendation”, Yin et al. make an eloquent argument that the long tail is where organizations can create the most value for their consumers. They also argue that existing recommender systems operate fundamentally different for long tail products than for mainstream goods. While matrix factorization, nearest-neighbors, and clustering work well for the “head” market, the long tail is better represented by a graph; specifically a bipartite graph that connects a set of users to a set of goods. In this paper, we show the algorithms presented by Yin et al., as well as a set of similar algorithms proposed by Shang et al., which traverse the bipartite graphs through a random walker in order to identify similar users and products. We build on elements from each work, as well as elements from a Markov process, to facilitate the random walker's traversal of the graph into the long tail regions. This method specifically constructs paths into regions of the long tail that are favorable to users.

Given that the Internet and sophisticated transportation networks have made an increasingly huge number of products and services available to the public, consumers are unable to identify, much less evaluate the usefulness of, such goods accessible to them. Modern recommendation systems filter out products of lesser utility to the customer, showcasing those items of higher preference to the user. While current state-of-the-art recommendation systems perform fairly well, they generally do better at recommending the popular subset of all products available rather than matching consumers with the vast amount of niche products in what has been termed the "Long Tail". In their seminal work, "Challenging the Long Tail Recommendation", Yin et al. make an eloquent argument that the long tail is where organizations can create the most value for their consumers. They also argue that existing recommender systems operate fundamentally different for long tail products than for mainstream goods. While matrix factorization, nearest-neighbors, and clustering work well for the "head" market, the long tail is better represented by a graph, specifically a bipartite graph that connects a set of users to a set of goods. In this paper, we discuss the algorithms presented by Yin et al., as well as a set of similar algorithms proposed by Shang et al., which traverse the bipartite graphs through a random walker in order to identify similar users and products. We build on elements from each work, as well as elements from a Markov process, to facilitate the random walker's traversal of tripartitle graphs into the long tail regions. This method specifically constructs paths into regions of the long tail that are favorable to users.

This article reports two experiments testing how managers’ capital allocation decisions are affected by where and to whom they report corporate social responsibility (CSR) information. Drawing on accountability theory, I predict that managers allocate more money to CSR activities when that information is reported in a dedicated CSR report that is intended for all stakeholders, compared to settings where it is reported in a financial report or when the information is intended specifically for capital providers. I find support for this prediction using graduate business students (Experiment 1) as participants, but not Mechanical Turk workers (Experiment 2). However, exploratory analyses indicate that my prediction is supported in Experiment 2 among millennial participants and that this result is attributable to participant age rather than work experience or preferences for CSR. This generational difference between millennials and non-millennials is consistent with recent research suggesting millennials are particularly sensitive to accountability pressures.

Managers prepare corporate social responsibility (CSR) reports by recalling and describing their past socially responsible actions. Using an experiment, we test whether the manner in which managers prepare CSR reports influences their subsequent ethical decisions. CSR reporting guidelines and firm policies can affect whether managers construe their past socially responsible actions abstractly or concretely (i.e., whether they focus on the underlying reason/purpose of the action or focus on the manner in which it was carried out). Drawing on identity theory and construal level theory, we predict and find that managers subsequently act more ethically if they construe their past socially responsible actions abstractly as opposed to concretely. Further, their ethical decisions are similar regardless of whether their past socially responsible action benefitted or harmed their personal welfare. We also find that the effect of construal reverses when managers prepare reports about past self-interested actions (i.e., actions that benefit the manager but harm others). We discuss practical implications of our results for standard setters, regulators, and senior executives responsible for creating external and internal CSR reporting guidelines.