Search results

Experiments are the backbone of the development process of data-driven predictive models for scientific applications. The quality of the experiments directly impacts the model performance. Uncertainty inherently affects experiment measurements and is often missing in the available data sets due to its estimation cost. For similar reasons, experiments are very few compared to other data sources. Discarding experiments based on the missing uncertainty values would preclude the development of predictive models. Data profiling techniques are fundamental to assess data quality, but some data quality dimensions are challenging to evaluate without knowing the uncertainty. In this context, this paper aims to predict the missing uncertainty of the experiments.

This work presents a methodology to forecast the experiments’ missing uncertainty, given a data set and its ontological description. The approach is based on knowledge graph embeddings and leverages the task of link prediction over a knowledge graph representation of the experiments database. The validity of the methodology is first tested in multiple conditions using synthetic data and then applied to a large data set of experiments in the chemical kinetic domain as a case study.

The analysis results of different test case scenarios suggest that knowledge graph embedding can be used to predict the missing uncertainty of the experiments when there is a hidden relationship between the experiment metadata and the uncertainty values. The link prediction task is also resilient to random noise in the relationship. The knowledge graph embedding outperforms the baseline results if the uncertainty depends upon multiple metadata.

The employment of knowledge graph embedding to predict the missing experimental uncertainty is a novel alternative to the current and more costly techniques in the literature. Such contribution permits a better data quality profiling of scientific repositories and improves the development process of data-driven models based on scientific experiments.

The purpose of this study is to extend the research on fashion renting (FR) by investigating how personal and social motives (i.e. “subjective norms”, “perceived behavioural control”, “sustainable orientation” and “FR benefits”) affect consumers’ attitudes and intentions towards it. In addition, personality traits are investigated as potential antecedents of FR, resulting in the proposal of an overall framework that combines the theory of planned behaviour with the trait theory approach.

Data were collected in Italy from a sample of 694 consumers, mainly females (88%), with an average age of 28.8 years and coming from all over the country. The collected data were then processed via structural equation modelling.

The results indicated that intention towards FR is influenced by attitude, which, in turn, is affected by social norms, perceived behavioural control, sustainable orientation and FR benefits. Furthermore, only fashion leadership acts as a direct antecedent of FR attitude, while the need for uniqueness and materialism plays critical roles as predictors of personal and social motives. Subjective norms and perceived behavioural control also serve as mediators of the significant relationships between personality traits and attitudes towards FR.

The study provides useful implications for fashion rental companies in attracting consumers and offers a foundation for further research on transforming traditional consumption into a more sustainable one.

The study presents new knowledge on the rental phenomenon in the fashion sector by responding to the call to deepen the analysis of factors that influence consumers’ adoption of FR from the perspectives of personal and social motives and personality traits.