Investor attention, analyst recommendation revisions, and stock prices

We provide evidence that investors underreact after analysts' recommendation upgrades; however, price reactions are faster after downgrades. We measure individual investors' attention using Google's search volume index. Our findings indicate that, after upgrades, stocks that enjoy greater individual investors' attention underreact significantly more compared to stocks that receive high level of attention from institutional investors. On the other hand, after recommendation downgrades, stocks with higher levels of prior attention from individual investors overreact and show a significantly greater price reversal compared to stocks that received high level of attention from institutional investors. Our results suggest that attentive individual investors may not be rational; hence investor attention and investor sophistication are important for price discovery in the market.

The Post-revision drift, analyst characteristics and investor attention

The aim of this dissertation is to provide a coherent explanation for the post-analyst recommendation drift. First, I find that the post-analyst recommendation drift is explained by the degree of attention paid by individual investors. Second I find that the extremeness and the credibility of information leads to changes in the degree of attention and a post-analyst recommendation drift. Finally, I find that the diffusion of private information contained in the analyst recommendation interacts with attention related biases leading to a post-recommendation drift.

An adaptive information grid architecture for recommendation system

This paper presents an adaptive information grid architecture for recommendation systems, which consists of the features of the recommendation rule and a co-citation algorithm. The algorithm addresses some challenges that are essential for further searching and recommendation algorithms. It does not require users to provide a lot of interactive communication. Furthermore, it supports other queries, such as keyword, URL and document investigations. When the structure is compared to other algorithms, the scalability is noticeably better. The high online performance can be obtained as well as the repository computation, which can achieve a high group-forming accuracy using only a fraction of web pages from a cluster.

A co-recommendation algorithm for web searching

This paper presents an approach called the Co-Recommendation Algorithm, which consists of the features of the recommendation rule and the co-citation algorithm. The algorithm addresses some challenges that are essential for further searching and recommendation algorithms. It does not require users to provide a lot of interactive communication. Furthermore, it supports other queries, such as keyword, URL and document investigations. When the structure is compared to other algorithms, the scalability is noticeably easier. The high online performance can be obtained as well as the repository computation, which can achieve a high group-forming accuracy using only a fraction of Web pages from a cluster.

Preference networks : probabilistic models for recommendation systems

Recommender systems are important to help users select relevant and personalised information over massive amounts of data available. We propose an unified framework called Preference Network (PN) that jointly models various types of domain knowledge for the task of recommendation. The PN is a probabilistic model that systematically combines both content-based filtering and collaborative filtering into a single conditional Markov random field. Once estimated, it serves as a probabilistic database that supports various useful queries such as rating prediction and top-N recommendation. To handle the challenging problem of learning large networks of users and items, we employ a simple but effective pseudo-likelihood with regularisation. Experiments on the movie rating data demonstrate the merits of the PN.

Impact of personalized recommendation and social comparison on learning behaviours and outcomes

ELearning suffers from the lack of face-to-face interaction and can deprive learners from the benefits of social interaction and comparison. In this paper we present the results of a study conducted for the impact of social comparison. The study was conducted by collecting students’ engagement with an eLearning tool, the attendance, and grades scored by students at specific milestones and presented these metrics to students as feedback using Kiviat charts. The charts were complemented with appropriate recommendations to allow them to adapt their study strategy and behaviour. The study spanned over 4 semesters (2 with and 2 without the Kiviats) and the results were analysed using paired T tests to test the pre and post results on topics covered by the eLearning tool. Survey questionnaires were also administered at the end for qualitative analysis. The results indicated that the Kiviat feedback with recommendation had positive impact on learning outcomes and attitudes.

Recommendation techniques based on off-line data processing: a multifaceted survey

Recommendations based on off-line data processing has attracted increasing attention from both research communities and IT industries. The recommendation techniques could be used to explore huge volumes of data, identify the items that users probably like, and translate the research results into real-world applications, etc. This paper surveys the recent progress in the research of recommendations based on off-line data processing, with emphasis on new techniques (such as context-based recommendation, temporal recommendation), and new features (such as serendipitous recommendation). Finally, we outline some existing challenges for future research.

Can analyst coverage reduce the incidence of fraud? Evidence from China

We investigate the impact of security analyst coverage on the incidence of corporate financial fraud in China. After controlling for the endogeneity between analyst following and fraud, we find that financial analyst coverage cannot significantly influence the incidence of fraud. The empirical findings suggest that financial analysts do not serve as external monitors to managers and large shareholders in China. © 2014 Taylor & Francis.

Modeling dual role preferences for trust-aware recommendation

Unlike in general recommendation scenarios where a user has only a single role, users in trust rating network, e.g. Epinions, are associated with two different roles simultaneously: as a truster and as a trustee. With different roles, users can show distinct preferences for rating items, which the previous approaches do not involve. Moreover, based on explicit single links between two users, existing methods can not capture the implicit correlation between two users who are similar but not socially connected. In this paper, we propose to learn dual role preferences (truster/trustee-specific preferences) for trust-aware recommendation by modeling explicit interactions (e.g., rating and trust) and implicit interactions. In particular, local links structure of trust network are exploited as two regularization terms to capture the implicit user correlation, in terms of truster/trustee-specific preferences. Using a real-world and open dataset, we conduct a comprehensive experimental study to investigate the performance of the proposed model, RoRec. The results show that RoRec outperforms other trust-aware recommendation approaches, in terms of prediction accuracy. Copyright 2014 ACM.

Deferentially private tagging recommendation based on topic model

Tagging recommender system allows Internet users to annotate resources with personalized tags and provides users the freedom to obtain recommendations. However, It is usually confronted with serious privacy concerns, because adversaries may re-identify a user and her/his sensitive tags with only a little background information. This paper proposes a privacy preserving tagging release algorithm, PriTop, which is designed to protect users under the notion of differential privacy. The proposed PriTop algorithm includes three privacy preserving operations: Private Topic Model Generation structures the uncontrolled tags, Private Weight Perturbation adds Laplace noise into the weights to hide the numbers of tags; while Private Tag Selection finally finds the most suitable replacement tags for the original tags. We present extensive experimental results on four real world datasets and results suggest the proposed PriTop algorithm can successfully retain the utility of the datasets while preserving privacy. © 2014 Springer International Publishing.

Preference Networks: probabilistic models for recommendation systems

Abstract
Recommender systems are important to help users select relevant and personalised information over massive amounts of data available. We propose an unified framework called Preference Network (PN) that jointly models various types of domain knowledge for the task of recommendation. The PN is a probabilistic model that systematically combines both content-based filtering and collaborative filtering into a single conditional
Markov random field. Once estimated, it serves as a probabilistic database that supports various useful queries such as rating prediction and top-N recommendation. To handle the challenging problem of learning large networks of users and items, we employ a simple but effective pseudo-likelihood with regularisation. Experiments on the movie rating data demonstrate the merits of the PN.

The use and abuse of 'community' and 'neighbourhood' within disability research: an exposé, clarification, and recommendation

Almost invariably in the disability literature, the terms 'neighbourhood' and 'community' are used as though they have some commonly understood meaning. They do not, and authors rarely offer a definition. This problem adds opacity to the literature describing people's living environment and the nature of their interaction with others living in the same area. This ambiguity becomes crucial to understanding when these terms are linked to other vague, but emotionally-charged words, such as 'inclusion' or 'integration'. This review presents some of the ways 'neighbourhood' and 'community' may be correctly employed. It also explores the theoretical basis for understanding how and why their use may be misleading. Finally, it is demonstrated that the assumed relevance of neighbourhood participation for life quality has been greatly exaggerated. We recommend that authors carefully define their use of these terms in order to facilitate understanding free from emotional bias.

Gender-diverse boards and properties of analyst earnings forecasts

Using a sample of 2,200 U.S. listed firm-year observations (2001-2007), this study shows a positive (negative) relation between gender diversity on corporate boards and analysts' earnings forecast accuracy (dispersion), after controlling for earnings quality, corporate governance, audit quality, stock price informativeness, and potential endogeneity. Our findings are important as they suggest that board diversity adds to the transparency and accuracy of financial reports such that earnings expectations are likely to be more accurate for these firms.