Alison Watkins

Evolutionary test data generation: a comparison of fitness functions

Previous research using genetic algorithms to automate the generation of data for path testing has utilized several different fitness functions, assessing their usefulness by comparing them to random generation. This paper describes two sets of experiments that assess the performance of several fitness functions, relative to one another and to random generation. The results demonstrate that some fitness functions provide better results than others, generating fewer test cases to exercise a given program path. In these studies, the branch predicate and inverse path probability approaches were the best performers, suggesting that a two‐step process combining these two methods may be the most efficient and effective approach to path testing. Copyright

MOGUL GAMES: IN DEFENSE OF INEQUALITY AS AN EVOLUTIONARY STRATEGY TO COPE WITH MULTIPLE AGENTS OF SELECTION

In this paper, we propose that the “powerful and privileged” sustain their way of life through greed and they sustain the lives of others through trickledown sharing. Greed provides the powerful and privileged a buffer against famine. Trickledown sharing provides them a buffer against predation or war. The inspiration for this integration of greed and trickledown sharing as self-preservation strategies is a multi-selection model called skew selection. According to skew selection, when perennial organisms are subjected to cycles of famine and predation, greed and trickledown sharing increases the organism’s survival relative to a greed-only strategy. Skew selection is extended to explain greed and trickledown sharing among humans through the introduction of mogul games. The results of mogul games reported herein suggest that inequality is an emergent property of self-organizing systems and potentially an essential precursor to the evolution of social behavior. In the future, it is our hope that mogul game simulations will be employed by others to explore the effect of variation in cycles of predation and resource abundance on the rules of greed (resource acquisition) and trickledown sharing (resources redistribution).

Clusters of entrepreneurs

Purpose – Entrepreneurs operate in conditions of dynamic uncertainty; identifying and exploiting opportunities presented by the business environment. Opportunistic search is core to entrepreneurial activity, but its dynamics are rarely explored. Groups of entrepreneurs are attracted to the same potential business opportunities. They have no incentive to cooperate, they may not even know of the existence of others. However, over time, clusters of entrepreneurs interested in the same opportunities develop. Aims to discuss the issues.Design/methodology/approach – Ant colony optimisation modelling is used to simulate the activities of entrepreneurs in an opportunity rich environment. The entrepreneurs must identify the locations of the appropriate resources. Three simulations were run to observe entrepreneurial success in different environments.Findings – A random search of the business environment for resources by individual entrepreneurs was unproductive. Once the entrepreneurs learned to read the business ...

A Data Snapshot Approach for Making Real-Time Predictions in Basketball

This article proposes a novel approach, called data snapshots, to generate real-time probabilities of winning for National Basketball Association (NBA) teams while games are being played. The approach takes a snapshot from a live game, identifies historical games that have the same snapshot, and uses the outcomes of these games to calculate the winning probabilities of the teams in this game as the game is underway. Using data obtained from 20 seasons worth of NBA games, we build three models and compare their accuracies to a baseline accuracy. In Model 1, each snapshot includes the point difference between the home and away teams at a given second of the game. In Model 2, each snapshot includes the net team strength in addition to the point difference at a given second. In Model 3, each snapshot includes the rate of score change in addition to the point difference at a given second. The results show that all models perform better than the baseline accuracy, with Model 1 being the best model.

How honest are the signals? A protocol for validating wearable sensors.

There is growing interest among organizational researchers in tapping into alternative sources of data beyond self-reports to provide a new avenue for measuring behavioral constructs. Use of alternative data sources such as wearable sensors is necessary for developing theory and enhancing organizational practice. Although wearable sensors are now commercially available, the veracity of the data they capture is largely unknown and mostly based on manufacturers’ claims. The goal of this research is to test the validity and reliability of data captured by one such wearable badge (by Humanyze) in the context of structured meetings where all individuals wear a badge for the duration of the encounter. We developed a series of studies, each targeting a specific sensor of this badge that is relevant for structured meetings, and we make specific recommendations for badge data usage based on our validation results. We have incorporated the insights from our studies on a website that researchers can use to conduct validation tests for their badges, upload their data, and assess the validity of the data. We discuss this website in the corresponding studies.