To implement machine learning, it is essential to first determine an appropriate algorithm for the dataset. Different algorithms may produce a large number of different models with different hyperparameter configurations, and it usually takes a lot of time to run the model on a large dataset when the model is relatively complex. Therefore, how to predict the performance of a model on a dataset is an fundamental problem to be solved. This thesis designs a prediction system based on matrix factorization to predict the classification accuracy of a specific model on a particular dataset. In this thesis, we conduct a comprehensive empirical research on more than fifty datasets that we collected from the openml web site.

Machine Learning (ML) software has been widely adopted in modern society, with reported fairness implications for minority groups based on race, sex, age, etc. Many recent works have proposed methods to measure and mitigate algorithmic bias in ML models. The existing approaches focus on single classifier-based ML models. However, real-world ML models are often composed of multiple independent or dependent learners in an ensemble (e.g., Random Forest), where the fairness composes in a non-trivial way. How does fairness compose in ensembles? What are the fairness impacts of the learners on the ultimate fairness of the ensemble? Can fair learners result in an unfair ensemble? Furthermore, studies have shown that hyperparameters influence the fairness of ML models. Ensemble hyperparameters are more complex since they affect how learners are combined in different categories of ensembles. Understanding the impact of ensemble hyperparameters on fairness will help programmers design fair ensembles. Today, we do not understand these fully for different ensemble algorithms. In this paper, we comprehensively study popular real-world ensembles: bagging, boosting, stacking and voting. We have developed a benchmark of 168 ensemble models collected from Kaggle on four popular fairness datasets. We use existing fairness metrics to understand the composition of fairness. Our results show that ensembles can be designed to be fairer without using mitigation techniques. We also identify the interplay between fairness composition and data characteristics to guide fair ensemble design. Finally, our benchmark can be leveraged for further research on fair ensembles. To the best of our knowledge, this is one of the first and largest studies on fairness composition in ensembles yet presented in the literature.

As the availability, size and complexity of data have increased in recent years, machine learning (ML) techniques have become popular for modeling. Predictions resulting from applying ML models are often used for inference, decision-making, and downstream applications. A crucial yet often overlooked aspect of ML is uncertainty quantification, which can significantly impact how predictions from models are used and interpreted. Extreme Gradient Boosting (XGBoost) is one of the most popular ML methods given its simple implementation, fast computation, and sequential learning, which make its predictions highly accurate compared to other methods. However, techniques for uncertainty determination in ML models such as XGBoost have not yet been universally agreed among its varying applications. We propose enhancements to XGBoost whereby a modified quantile regression is used as the objective function to estimate uncertainty (QXGBoost). Specifically, we included the Huber norm in the quantile regression model to construct a differentiable approximation to the quantile regression error function. This key step allows XGBoost, which uses a gradient-based optimization algorithm, to make probabilistic predictions efficiently. QXGBoost was applied to create 90\% prediction intervals for one simulated dataset and one real-world environmental dataset of measured traffic noise. Our proposed method had comparable or better performance than the uncertainty estimates generated for regular and quantile light gradient boosting. For both the simulated and traffic noise datasets, the overall performance of the prediction intervals from QXGBoost were better than other models based on coverage width-based criterion.

Traffic congestion caused by non-recurring incidents such as vehicle crashes and debris is a key issue for Traffic Management Centers (TMCs). Clearing incidents in a timely manner is essential for improving safety and reducing delays and emissions for the traveling public. However, TMCs and other responders face a challenge in predicting the duration of incidents (until the roadway is clear), making decisions of what resources to deploy difficult. To address this problem, this research developed an analytical framework and end-to-end machine-learning solution for predicting incident duration based on information available as soon as an incident report is received. Quality predictions of incident duration can help TMCs and other responders take a proactive approach in deploying responder services such as tow trucks, maintenance crews or activating alternative routes. The predictions use a combination of classification and regression machine learning modules. The performance of the developed solution has been evaluated based on the Mean Absolute Error (MAE), or deviation from the actual incident duration as well as Area Under the Curve (AUC) and Mean Absolute Percentage Error (MAPE). The results showed that the framework significantly improved incident duration prediction compared to methods from previous research.

Improving the fairness of machine learning models is a nuanced task that requires decision makers to reason about multiple, conflicting criteria. The majority of fair machine learning methods transform the error-fairness trade-off into a single objective problem with a parameter controlling the relative importance of error versus fairness. We propose instead to directly optimize the error-fairness tradeoff by using multi-objective optimization. We present a flexible framework for defining the fair machine learning task as a weighted classification problem with multiple cost functions. This framework is agnostic to the underlying prediction model as well as the metrics. We use multiobjective optimization to define the sample weights used in model training for a given machine learner, and adapt the weights to optimize multiple metrics of fairness and accuracy across a set of tasks. To reduce the number of optimized parameters, and to constrain their complexity with respect to population subgroups, we propose a novel meta-model approach that learns to map protected attributes to sample weights, rather than optimizing those weights directly. On a set of real-world problems, this approach outperforms current state-of-the-art methods by finding solution sets with preferable error/fairness trade-offs.

We present Classy Ensemble, a novel ensemble-generation algorithm for classification tasks, which aggregates models through a weighted combination of per-class accuracy. Tested over 153 machine learning datasets we demonstrate that Classy Ensemble outperforms two other well-known aggregation algorithms -- order-based pruning and clustering-based pruning -- as well as the recently introduced lexigarden ensemble generator. We then present three enhancements: 1) Classy Cluster Ensemble, which combines Classy Ensemble and cluster-based pruning; 2) Deep Learning experiments, showing the merits of Classy Ensemble over four image datasets: Fashion MNIST, CIFAR10, CIFAR100, and ImageNet; and 3) Classy Evolutionary Ensemble, wherein an evolutionary algorithm is used to select the set of models which Classy Ensemble picks from.

Mental illnesses are one of the most prevalent public health problems worldwide, which negatively influence people's lives and society's health. With the increasing popularity of social media, there has been a growing research interest in the early detection of mental illness by analysing user-generated posts on social media. According to the correlation between emotions and mental illness, leveraging and fusing emotion information has developed into a valuable research topic. In this article, we provide a comprehensive survey of approaches to mental illness detection in social media that incorporate emotion fusion. We begin by reviewing different fusion strategies, along with their advantages and disadvantages. Subsequently, we discuss the major challenges faced by researchers working in this area, including issues surrounding the availability and quality of datasets, the performance of algorithms and interpretability. We additionally suggest some potential directions for future research.

Researchers have proposed many methods for fair and robust machine learning, but comprehensive empirical evaluation of their subgroup robustness is lacking. In this work, we address this gap in the context of tabular data, where sensitive subgroups are clearly-defined, real-world fairness problems abound, and prior works often do not compare to state-of-the-art tree-based models as baselines. We conduct an empirical comparison of several previously-proposed methods for fair and robust learning alongside state-of-the-art tree-based methods and other baselines. Via experiments with more than $340{,}000$ model configurations on eight datasets, we show that tree-based methods have strong subgroup robustness, even when compared to robustness- and fairness-enhancing methods. Moreover, the best tree-based models tend to show good performance over a range of metrics, while robust or group-fair models can show brittleness, with significant performance differences across different metrics for a fixed model. We also demonstrate that tree-based models show less sensitivity to hyperparameter configurations, and are less costly to train. Our work suggests that tree-based ensemble models make an effective baseline for tabular data, and are a sensible default when subgroup robustness is desired. For associated code and detailed results, see https://github.com/jpgard/subgroup-robustness-grows-on-trees .

Explainability in yield prediction helps us fully explore the potential of machine learning models that are already able to achieve high accuracy for a variety of yield prediction scenarios. The data included for the prediction of yields are intricate and the models are often difficult to understand. However, understanding the models can be simplified by using natural groupings of the input features. Grouping can be achieved, for example, by the time the features are captured or by the sensor used to do so. The state-of-the-art for interpreting machine learning models is currently defined by the game-theoretic approach of Shapley values. To handle groups of features, the calculated Shapley values are typically added together, ignoring the theoretical limitations of this approach. We explain the concept of Shapley values directly computed for predefined groups of features and introduce an algorithm to compute them efficiently on tree structures. We provide a blueprint for designing swarm plots that combine many local explanations for global understanding. Extensive evaluation of two different yield prediction problems shows the worth of our approach and demonstrates how we can enable a better understanding of yield prediction models in the future, ultimately leading to mutual enrichment of research and application.

However, the existence of automated accounts, also known as social bots, has brought many problems to social media. These bots have been employed to disseminate false information, manipulate elections, and deceive users, resulting in negative societal consequences [1; 2; 3]. Effectively detecting bots on social media plays an important role in protecting user interests and ensuring stable platform operation. Therefore, the accurate detection of bots on social media platforms is becoming increasingly crucial. Random Forest (RF) [4] is a classical algorithm of ensemble learning that can significantly improve the performance of the base classifier, Decision Tree (DT) [5]. Specifically, S sub-training sets are generated by randomly selecting n samples with replacement from the original training set of N samples S times. Then, m features are selected from the M-dimensional features of each sub-training set, and S base classifiers are trained using different sub-training sets. The final classification result is determined by the voting of the base classifiers. Due to its excellent performance, RF has been widely applied in various competitions, such as data mining and financial risk detection, and is also frequently used in social bot detection.