Search results

The rapid advancement of artificial intelligence (AI), particularly within the last decade and the application of ‘deep learning’, has simultaneously accelerated human fears of the changes AI provokes in human behaviour. The question is not any more if the new phenomena, like artificially-induced consciousness, empathy or creation, will be widely used, but whether they will be used in ethically acceptable ways and for ethically acceptable purposes.

Departing from a diagnosis of the state humans have brought themselves to by (ab)use of technology, the present chapter investigates the possibility of a systematic study of adaptations human society will have to consider in order to guarantee the obeyance to the fundamental ethical values and thus its spiritual survival. To that end, a new discipline – epharmology (from the Greek epharmozein = to adapt) is proposed, together with its aims and methodology.

This paper aims to discuss the scholarship over the past 30 years on what used to be called Melanesian warfare or “tribal fighting” and is termed in this paper “intergroup conflict” in the Highlands of Papua New Guinea. The paper categorises the drivers of intergroup conflict that make up the landscape for conflict in the Highlands. It starts with cultural factors and the understandings about conflict that have long been used to explain such violence, then adds newer factors. It argues that while the individual existence of each driver is important, far more important is the way in which they interact with each other in reinforcing feedback loops that propel the actors involved towards violence.

The paper is based on a thorough review of the scholarly and grey literature on the topic, drawing from the fields of anthropology, criminology, political science, law, justice and peacebuilding.

The overall finding of the paper is that the nature of intergroup conflict, its scale and dynamics, has changed considerably over the past 30 years, most prominently in the entanglement of the state with local-level conflicts. This has significantly affected the nature of intergroup conflict today, deepening the attractors towards violence and conflict, while weakening the ability of existing state and non-state systems to prevent it. The picture that emerges is one in which the interconnectivity of factors promoting violence has intensified, the rate of change is accelerating and levels of violence are amplified.

This paper is an original work.

Product returns are a major challenge for e-businesses as they involve huge logistical and operational costs. Therefore, it becomes crucial to predict returns in advance. This study aims to evaluate different genres of classifiers for product return chance prediction, and further optimizes the best performing model.

An e-commerce data set having categorical type attributes has been used for this study. Feature selection based on chi-square provides a selective features-set which is used as inputs for model building. Predictive models are attempted using individual classifiers, ensemble models and deep neural networks. For performance evaluation, 75:25 train/test split and 10-fold cross-validation strategies are used. To improve the predictability of the best performing classifier, hyperparameter tuning is performed using different optimization methods such as, random search, grid search, Bayesian approach and evolutionary models (genetic algorithm, differential evolution and particle swarm optimization).

A comparison of F1-scores revealed that the Bayesian approach outperformed all other optimization approaches in terms of accuracy. The predictability of the Bayesian-optimized model is further compared with that of other classifiers using experimental analysis. The Bayesian-optimized XGBoost model possessed superior performance, with accuracies of 77.80% and 70.35% for holdout and 10-fold cross-validation methods, respectively.

Given the anonymized data, the effects of individual attributes on outcomes could not be investigated in detail. The Bayesian-optimized predictive model may be used in decision support systems, enabling real-time prediction of returns and the implementation of preventive measures.

There are very few reported studies on predicting the chance of order return in e-businesses. To the best of the authors’ knowledge, this study is the first to compare different optimization methods and classifiers, demonstrating the superiority of the Bayesian-optimized XGBoost classification model for returns prediction.