Browse Articles

Machine learning algorithms are becoming increasingly popular for data crunching across a vast area of scientific disciplines. Here, the authors compare two machine learning algorithms with respect to accuracy and user-friendliness and find that random forest algorithms outperform logistic regression when applied to the same dataset.

Machine learning systems are often expected to make fair decisions, yet the most widely used fairness criteria—independence, separation, and sufficiency—cannot generally be satisfied at the same time. In this study, students tested these criteria using a logistic regression model on a real-world student performance dataset and found that each criterion was met only at different prediction thresholds, with no threshold satisfying all three simultaneously. These results illustrate the inherent trade-offs in algorithmic fairness and highlight why achieving perfectly fair machine learning models is often impossible in practice.

Given an association between nicotine addiction and gene expression, we hypothesized that expression of genes commonly associated with smoking status would have variable expression between smokers and non-smokers. To test whether gene expression varies between smokers and non-smokers, we analyzed two publicly-available datasets that profiled RNA gene expression from brain (nucleus accumbens) and lung tissue taken from patients identified as smokers or non-smokers. We discovered statistically significant differences in expression of dozens of genes between smokers and non-smokers. To test whether gene expression can be used to predict whether a patient is a smoker or non-smoker, we used gene expression as the training data for a logistic regression or random forest classification model. The random forest classifier trained on lung tissue data showed the most robust results, with area under curve (AUC) values consistently between 0.82 and 0.93. Both models trained on nucleus accumbens data had poorer performance, with AUC values consistently between 0.65 and 0.7 when using random forest. These results suggest gene expression can be used to predict smoking status using traditional machine learning models. Additionally, based on our random forest model, we proposed KCNJ3 and TXLNGY as two candidate markers of smoking status. These findings, coupled with other genes identified in this study, present promising avenues for advancing applications related to the genetic foundation of smoking-related characteristics.

COVID-19 has impacted the way many people go about their daily lives, but what are the main factors driving the changes in the housing market, particular house prices?

The global issue of water quality has led to the use of machine learning models, like ANN and SVM, to predict water potability. However, these models can be complex and resource-intensive. This research aimed to find a simpler, more efficient model for water quality prediction.

The authors looked at the relationship between unemployment and minimum wage in Turkey (Türkiye). They found that there is a positive correlation between minimum wage and unemployment.

Tax incentives for sustainable technology are a key part of the push for a greener future. However, these incentives may not reach all income strata equally. Using a machine learning approach, this study analyzed the distributional effects of residential energy tax credits across different income levels in the United States.

Iridescent materials reflect different colored depending on viewing angle. This specific effect can be achieved by biomimetic photonic materials. This project models the quantitative relationship between these material’s coloring and its nanostructure to facilitate personalized design of art materials.

The authors looked at unionization petitions from Starbucks workers between August 2021 and July 2024 to determine what factors influence votes for or against unionization.

The authors looked at the ability of different machine learning algorithms to predict the level of financial corruption in different countries.