Leid Zejnilovic

Universidade NOVA de Lisboa | NOVA · Nova School of Business and Economics (SBE)

An algorithm effects a causal representation of relations between features and labels in the human’s perception. Such a representation might conflict with the human’s prior belief. Explanations can direct the human’s attention to the conflicting feature and away from other relevant features. This leads to causal overattribution and may adversely af...

There is growing evidence of the differential effects the COVID-19 pandemic had on small-scale fisheries across the world, with predominantly decreased landings during the time of restrictions and substantial negative socio-economic impact. We contribute to this evidence with an analysis of a comprehensive dataset of 5 million first sales of seafoo...

Ever since there has been an organized collection and use of data for informing decision making, there has been a debate about the extent to which these data have been put to the best use for improving social welfare in terms of general well-being of a community or an entire society. This chapter offers a contribution to that debate, showing how di...

Abstract: Predicting students’ retention risk is one of the major trends in machine learning applications in education. While early identification of at-risk students allows timely planning and implementation of measures to prevent adverse outcomes, there is a trade-off between the predictive model’s performance and the prediction window size, or m...

Multisided platforms are new organizing forms that can boost innovation in the healthcare sector by empowering patients as innovators and facilitating the commercialization of innovations by and for patients. However, applying the playbook script for the platform model from other sectors may prove challenging given the distinctive nature of the hea...

Decisions in organizations are about evaluating alternatives and choosing the one that would best serve organizational goals. To the extent that the evaluation of alternatives could be formulated as a predictive task with appropriate metrics, machine learning algorithms are increasingly being used to improve the efficiency of the process. Explanati...

Purpose The purpose of this paper is to propose and demonstrate how Tourism2vec, an adaptation of a natural language processing technique Word2vec, can serve as a tool to investigate tourism spatio-temporal behavior and quantifying tourism dynamics. Design/methodology/approach Tourism2vec, the proposed destination-tourist embedding model that lear...

The recent surge of interest in algorithmic decision-making among scholars across disciplines is associated with its potential to resolve the challenges common to administrative decision-making in the public sector, such as greater fairness and equal treatment of each individual, among others. However, algorithmic decision-making combined with huma...

The automotive industry, as other manufacturing industries, has evolved from competing on discrete transactions to relational agreements with customers. While previous literature calls for further analysis of the observed heterogeneity found across servitized manufacturing industries, this article contextualizes the analysis in the automotive indus...

Predictive models are used by public employment services to forecast registrants' risk of becoming long-term unemployed, and to develop proactive, preventative interventions to help them develop their skills and find work. Traditionally, simple statistical models are used due to their interpretability. However, we found that even simple models may...

We partner with a leading European healthcare provider and design a mechanism to match patients with family doctors in primary care. We define the matchmaking process for several distinct use cases given different levels of available information about patients. Then, we adopt a hybrid recommender system to present each patient a list of family doct...

Background There is growing evidence that many patients and caregivers innovate by developing new solutions to cope with their health disorders. Given the easy access to vast internet resources and peers globally, it is increasingly important to understand what may influence user innovation and its adoption in health for improving individual well-b...

BACKGROUND There is growing evidence that many patients and caregivers innovate by developing new solutions to cope with their health disorders. Given the easy access to vast internet resources and peers globally, it is increasingly important to understand what may influence user innovation and its adoption in health for improving individual well-b...

We propose a collaborative filtering recommender system to match patients with doctors in primary care. In particular, we model patient trust in primary care doctors using a large-scale dataset of consultation histories and account for the temporal dynamics of their relationships, defined in a novel quantitative measure of patient-doctor trust. Our...

In recent years, patients and informal caregivers have begun to play a much more prominent role in managing disease and participating in decisions about their treatment. However, the health care system has barely scratched the surface of their ability to innovate. Our research shows that patients and their caregivers are able to create many differe...

The innovation management literature recently brought forward an important, but largely ignored role that patients have in health care—as a source of important new solutions for medical care. Several studies have documented health-related innovations made by lay people, specifically the phenomenon of patient innovation and its potential to improve...

This paper is a multi-method study of the ways the patients solve their healthcare related problems by either developing a solution or adopting one developed by another patient. In the qualitative part of the study, we consider the patients’ problem-solving process with a focus only on patient-developments. Interpreting 30 cases collected by interv...

We measure and characterize innovation efforts by rare disease patients in Portugal, in a sample of 496 rare disease patients. We find that about 10% of the surveyed individuals innovate with some degree of newness, and no solution has introduced something radically new. Yet, their innovations have significant impact on their quality of life. Compa...

There is growing evidence that patients and their family members innovate in therapies, and medical devices. These patient innovators are increasingly recognized as an important source of innovation. However, little is known about the paths they take to validate their solutions before involving health regulators. We attempt to understand these patt...

We provide the first empirical exploration of disease-related innovation by patients and their caregivers. Our aims were to measure the frequency of innovation by these patients and their caregivers, and the improvement in well-being they experienced from using what they have developed. In addition, we explored the diffusion of their innovations to...

We analyze innovation proposals submitted by employees of a large information and communication technology firm to an idea management system (IMS). We find that employees innovate in various ways, including modifying internal processes, creating new products and services, or significantly changing the way the firm delivers an existing service. We a...

In this paper we proposed a novel algorithm DEOS (Divide, Explore, Optimize and Suggest) which provides simulation model for space exploration and path optimization, deploying network of mobile agents. Two-dimensional, unstructured environment with static obstacles is considered. In our approach the space is divided in two planes. The first plane,...

In this paper, optical signal detection in the presence of intersymbol interference, white Gaussian and pulse noise is considered. The bit error probability is calculated as a function of a signal to noise ratio, SNR, for a different value of the bit rate.