Archive ouverte de l'ESSEC Business School
Not a member yet
1344 research outputs found
Sort by
Extracting Unique Discussions of Interests for Entrepreneurs and Managers in a Set of Business Tweets Without Any Human Bias
No full textInternational audienceThis study proposes a framework for extracting unique discussions of the interests of managersand entrepreneurs on Twitter (X). By unique discussions of interests, we mean those that are more tweetedby these communities but rarely by public people. These discussions can be facts and/or sentiments related tosome topics. Since this is a subjective problem, human intervention can lead to bias in the results. Therefore,we propose an unsupervised method with zero information about the context since prior knowledge stemsfrom human intervention. Consequently, there is no real ground truth. To retrieve such discussions ofinterests, first, unique tweets (discussions) are identified in two stages. In the first stage, a scoring algorithmis proposed that gives a score to each tweet of a specific year and tweets are sorted based on their scores.Different sets of tweets are selected based on their scores and considered automatically created groundtruths. In the next stage, an unsupervised convolutional neural network trained on the created ground truth isused for the classification of tweets of other years (whether they are unique to these communities). Finally,latent Dirichlet analysis is applied to the detected unique tweets to give the most common interest topicsdiscussed by these communities. Experimental analysis is performed on tweets from 2017-2019. The resultsreveal these communities’ attitudes and highlight interesting common and different topics discussed betweenmanagers and entrepreneurs; some of them can be difficult for humans to predict in advance. The proposedapproach is applicable to any community
Variable selection, monotone likelihood ratio and group sparsity
No full textInternational audienceIn the pivotal variable selection problem, we derive the exact non-asymptotic minimax selector over the class of all s-sparse vectors, which is also the Bayes selector with respect to the uniform prior. While this optimal selector is, in general, not realizable in polynomial time, we show that its tractable counterpart (the scan selector) attains the minimax expected Hamming risk to within factor 2, and is also exact minimax with respect to the probability of wrong recovery. As a consequence, we establish explicit lower bounds under the monotone likelihood ratio property and we obtain a tight characterization of the minimax risk in terms of the best separable selector risk. We apply these general results to derive necessary and sufficient conditions of exact and almost full recovery in the location model with light tail distributions and in the problem of group variable selection under Gaussian nois
Instances and detailed results for the whole testbed of "A Branch-Price-and-Cut algorithm for the Multi-Commodity two-echelon Distribution Problem"
No full textInstances and detailed results for the whole testbed of "A Branch-Price-and-Cut algorithm for the Multi-Commodity two-echelon Distribution Problem
On the relation between extremal dependence and concomitants
No full textThe study of concomitants has recently met a renewed interest due to its applications in selection procedures. For instance, concomitants are used in rankedset sampling, to achieve efficiency and reduce cost when compared to the simple random sampling. In parallel, the search for new methods to provide a rich description of extremal dependence among multiple time series has rapidly grown, due also to its numerous practical implications and the lack of suitablemodels to assess it. Here, our aim is to investigate extremal dependence when choosing the concomitants approach. In this study, we show how the extremal dependence of a vector (X, Y) impacts the asymptotic behavior of the maximaover subsets of concomitants. Furthermore, discussing the various conditions and results, we investigate how transformations of the marginal distributions of X and Y influence the degeneracy of the limit
The role of prior warnings when cheating is easy and punishment is credible
No full textInternational audienceDuring the COVID-19 sanitary crisis, many exams were hastily moved to online mode. This revived a much needed debate over the privacy issues associated with online proctoring of exams, while the validity and fairness of unproctored exams were increasingly questioned. With a randomized control trial, we estimate the effectiveness of prior warnings as a means of discouraging academic dishonesty in exams. We use original, non-intrusive technologies to surreptitiously identify cheating in a series of unproctored assignments and send a targeted warning to half of the students who were identified as cheaters. We then compare their cheating behavior on the final exam with the behavior of the group of unwarned cheaters. The warning proves effective but does not completely eliminate cheating, as some students’ cheating strategies become more sophisticated following issuance of the warnings. We conclude that switching traditional exams to online mode should be accompanied by proctoring. When proctoring is not possible, credible and effective anti-cheating technologies should be deployed together with adequate warnings
A Failing Business Model In Sports Media? The Case Of Mediapro In The French Football Broadcasting Rights Market
No full textInternational audienc
Do sustainability signals diverge? An analysis of labeling schemes for socially responsible investments *
No full textSeveral labels for sustainable investment funds sponsored by government and nonprofitorganizations (GNPOs) have emerged in Europe. This paper examines the coherence ofthe signals sent by these sustainable labels versus those from the private sector. Whilesome GNPO-labeled funds are perceived as bearing high Environmental, Social andGovernance (ESG) risks, we find that labeled funds are more likely to be assessed as topESG funds by private rating providers. Furthermore, equity funds with governmental andmultiple labels are more likely to show better ESG ratings. Additionally, GNPO-labeledfunds show greater alignment with article 9 of the Sustainable Finance DisclosureRegulation and tend to exhibit ESG terminology in their name, consistent with internalsignals of sustainability coherence with GNPO labels. However, our research drawsattention to the existence of sustainable signals that are not always coherent,jeopardizing their role as efficient tools for promoting sustainability
Shaping control systems for corporate startup studios : A longitudinal analysis of La Fabrique by CA
No full textInternational audienc
Examen de quelques fondamentaux de la gouvernance d’entreprise – Conceptions de la gouvernance, rôle du Conseil, interpellation de la RSE et effets du devoir de vigilance
No full textAn exact algorithm for the Multi-Commodity two-echelon Distribution Problem
No full textInternational audienceWe consider a problem where multiple commodities are collected from the suppliers, sent to the distribution centres for consolidation purposes and delivered to the customers to fulfil their requests. We name it Multi-Commodity two-echelon Distribution Problem (MC2DP). The collection operations are performed by an unlimited fleet of homogeneous capacitated vehicles with direct trips from the suppliers to the distribution centres. Conversely, each distribution centre owns an unlimited fleet of homogeneous capacitated vehicles performing routes to deliver the commodities to the customers. All vehicles can transport any set of commodities as long as their capacity is not exceeded