More Accurate Learning of k-DNF Reference Classes

In machine learning, predictors trained on a given data distribution are usually guaranteed to perform well for further examples from the same distribution on average. This often may involve disregarding or diminishing the predictive power on atypical examples; or, in more extreme cases, a data distribution may be composed of a mixture of individually “atypical” heterogeneous populations, and the kind of simple predictors we can train may find it difficult to fit all of these populations simultaneously. In such cases, we may wish to make predictions for an atypical point by selecting a suitable reference class for that point: a subset of the data that is “more similar” to the given query point in an appropriate sense. Closely related tasks also arise in applications such as diagnosis or explaining the output of classifiers. We present new algorithms for computing k-DNF reference classes and establish much stronger approximation guarantees for their error rates.

Download Full-text

Race and Gender

The Oxford Handbook of Ethics of AI ◽

10.1093/oxfordhb/9780190067397.013.16 ◽

2020 ◽

pp. 251-269 ◽

Cited By ~ 2

Author(s):

Timnit Gebru

Keyword(s):

Machine Learning ◽

Language Processing ◽

The United States ◽

Error Rates ◽

Political Factors ◽

Recidivism Rates ◽

Race And Gender ◽

Decision Tools ◽

And Gender ◽

Technical Solutions

This chapter discusses the role of race and gender in artificial intelligence (AI). The rapid permeation of AI into society has not been accompanied by a thorough investigation of the sociopolitical issues that cause certain groups of people to be harmed rather than advantaged by it. For instance, recent studies have shown that commercial automated facial analysis systems have much higher error rates for dark-skinned women, while having minimal errors on light-skinned men. Moreover, a 2016 ProPublica investigation uncovered that machine learning–based tools that assess crime recidivism rates in the United States are biased against African Americans. Other studies show that natural language–processing tools trained on news articles exhibit societal biases. While many technical solutions have been proposed to alleviate bias in machine learning systems, a holistic and multifaceted approach must be taken. This includes standardization bodies determining what types of systems can be used in which scenarios, making sure that automated decision tools are created by people from diverse backgrounds, and understanding the historical and political factors that disadvantage certain groups who are subjected to these tools.

Download Full-text

Prediction and Analysis of the Severity and Number of Suburban Accidents Using Logit Model, Factor Analysis and Machine Learning: A case study in a developing country

SN Applied Sciences ◽

10.1007/s42452-020-04081-3 ◽

2021 ◽

Vol 3 (1) ◽

Author(s):

Meisam Ghasedi ◽

Maryam Sarfjoo ◽

Iraj Bargegol

Keyword(s):

Machine Learning ◽

Factor Analysis ◽

Logit Model ◽

Predictive Power ◽

Dominant Role ◽

Learning Approaches ◽

Lighting Condition ◽

Rainy Weather ◽

Pedestrian Accidents ◽

Effective Principal

AbstractThe purpose of this study is to investigate and determine the factors affecting vehicle and pedestrian accidents taking place in the busiest suburban highway of Guilan Province located in the north of Iran and provide the most accurate prediction model. Therefore, the effective principal variables and the probability of occurrence of each category of crashes are analyzed and computed utilizing the factor analysis, logit, and Machine Learning approaches simultaneously. This method not only could contribute to achieving the most comprehensive and efficient model to specify the major contributing factor, but also it can provide officials with suggestions to take effective measures with higher precision to lessen accident impacts and improve road safety. Both the factor analysis and logit model show the significant roles of exceeding lawful speed, rainy weather and driver age (30–50) variables in the severity of vehicle accidents. On the other hand, the rainy weather and lighting condition variables as the most contributing factors in pedestrian accidents severity, underline the dominant role of environmental factors in the severity of all vehicle-pedestrian accidents. Moreover, considering both utilized methods, the machine-learning model has higher predictive power in all cases, especially in pedestrian accidents, with 41.6% increase in the predictive power of fatal accidents and 12.4% in whole accidents. Thus, the Artificial Neural Network model is chosen as the superior approach in predicting the number and severity of crashes. Besides, the good performance and validation of the machine learning is proved through performance and sensitivity analysis.

Download Full-text

Machine Learning Methods Applied to the Prediction of Pseudo-nitzschia spp. Blooms in the Galician Rias Baixas (NW Spain)

ISPRS International Journal of Geo-Information ◽

10.3390/ijgi10040199 ◽

2021 ◽

Vol 10 (4) ◽

pp. 199

Author(s):

Francisco M. Bellas Aláez ◽

Jesus M. Torres Palenzuela ◽

Evangelos Spyrakos ◽

Luis González Vilas

Keyword(s):

Machine Learning ◽

Performance Metrics ◽

Prediction Models ◽

Support Vector ◽

False Alarms ◽

Learning Approaches ◽

Learning Methods ◽

Machine Learning Methods ◽

Rías Baixas ◽

New Algorithms

This work presents new prediction models based on recent developments in machine learning methods, such as Random Forest (RF) and AdaBoost, and compares them with more classical approaches, i.e., support vector machines (SVMs) and neural networks (NNs). The models predict Pseudo-nitzschia spp. blooms in the Galician Rias Baixas. This work builds on a previous study by the authors (doi.org/10.1016/j.pocean.2014.03.003) but uses an extended database (from 2002 to 2012) and new algorithms. Our results show that RF and AdaBoost provide better prediction results compared to SVMs and NNs, as they show improved performance metrics and a better balance between sensitivity and specificity. Classical machine learning approaches show higher sensitivities, but at a cost of lower specificity and higher percentages of false alarms (lower precision). These results seem to indicate a greater adaptation of new algorithms (RF and AdaBoost) to unbalanced datasets. Our models could be operationally implemented to establish a short-term prediction system.

Download Full-text

Application of machine learning-based models to boost the predictive power of the SPAN index

International Journal of Neuroscience ◽

10.1080/00207454.2021.1881092 ◽

2021 ◽

pp. 1-11

Author(s):

Chen-Chih Chung ◽

Oluwaseun Adebayo Bamodu ◽

Chien-Tai Hong ◽

Lung Chan ◽

Hung-Wen Chiu

Keyword(s):

Machine Learning ◽

Predictive Power

Download Full-text

Predicting Increased Blood Pressure Using Machine Learning

Journal of Obesity ◽

10.1155/2014/637635 ◽

2014 ◽

Vol 2014 ◽

pp. 1-12 ◽

Cited By ~ 31

Author(s):

Hudson Fernandes Golino ◽

Liliany Souza de Brito Amaral ◽

Stenio Fernando Pimentel Duarte ◽

Cristiano Mauro Assis Gomes ◽

Telma de Jesus Soares ◽

...

Keyword(s):

Machine Learning ◽

Blood Pressure ◽

Predictive Power ◽

Classification Tree ◽

Training Group ◽

Test Sample ◽

Hip Circumference ◽

Training Set ◽

Learning Technique ◽

Tree Data

The present study investigates the prediction of increased blood pressure by body mass index (BMI), waist (WC) and hip circumference (HC), and waist hip ratio (WHR) using a machine learning technique named classification tree. Data were collected from 400 college students (56.3% women) from 16 to 63 years old. Fifteen trees were calculated in the training group for each sex, using different numbers and combinations of predictors. The result shows that for women BMI, WC, and WHR are the combination that produces the best prediction, since it has the lowest deviance (87.42), misclassification (.19), and the higher pseudoR2(.43). This model presented a sensitivity of 80.86% and specificity of 81.22% in the training set and, respectively, 45.65% and 65.15% in the test sample. For men BMI, WC, HC, and WHC showed the best prediction with the lowest deviance (57.25), misclassification (.16), and the higher pseudoR2(.46). This model had a sensitivity of 72% and specificity of 86.25% in the training set and, respectively, 58.38% and 69.70% in the test set. Finally, the result from the classification tree analysis was compared with traditional logistic regression, indicating that the former outperformed the latter in terms of predictive power.

Download Full-text

Unraveling city-specific signature and identifying sample origin locations for the data from CAMDA MetaSUB challenge

Biology Direct ◽

10.1186/s13062-020-00284-1 ◽

2021 ◽

Vol 16 (1) ◽

Author(s):

Runzhi Zhang ◽

Alejandro R. Walker ◽

Susmita Datta

Keyword(s):

Machine Learning ◽

Error Rates ◽

Average Error ◽

Importance Score ◽

Learning Methods ◽

Principal Coordinates Analysis ◽

Principal Coordinates ◽

Total Variability ◽

The Common ◽

Feature Selecting

Abstract Background Composition of microbial communities can be location-specific, and the different abundance of taxon within location could help us to unravel city-specific signature and predict the sample origin locations accurately. In this study, the whole genome shotgun (WGS) metagenomics data from samples across 16 cities around the world and samples from another 8 cities were provided as the main and mystery datasets respectively as the part of the CAMDA 2019 MetaSUB “Forensic Challenge”. The feature selecting, normalization, three methods of machine learning, PCoA (Principal Coordinates Analysis) and ANCOM (Analysis of composition of microbiomes) were conducted for both the main and mystery datasets. Results Features selecting, combined with the machines learning methods, revealed that the combination of the common features was effective for predicting the origin of the samples. The average error rates of 11.93 and 30.37% of three machine learning methods were obtained for main and mystery datasets respectively. Using the samples from main dataset to predict the labels of samples from mystery dataset, nearly 89.98% of the test samples could be correctly labeled as “mystery” samples. PCoA showed that nearly 60% of the total variability of the data could be explained by the first two PCoA axes. Although many cities overlapped, the separation of some cities was found in PCoA. The results of ANCOM, combined with importance score from the Random Forest, indicated that the common “family”, “order” of the main-dataset and the common “order” of the mystery dataset provided the most efficient information for prediction respectively. Conclusions The results of the classification suggested that the composition of the microbiomes was distinctive across the cities, which could be used to identify the sample origins. This was also supported by the results from ANCOM and importance score from the RF. In addition, the accuracy of the prediction could be improved by more samples and better sequencing depth.

Download Full-text

Borderline and Depression: A Thin EEG Line

Clinical EEG and Neuroscience ◽

10.1177/15500594211060830 ◽

2021 ◽

pp. 155005942110608

Author(s):

Jakša Vukojević ◽

Damir Mulc ◽

Ivana Kinder ◽

Eda Jovičić ◽

Krešimir Friganović ◽

...

Keyword(s):

Machine Learning ◽

Borderline Personality ◽

Machine Learning Techniques ◽

Major Depressive ◽

Everyday Clinical Practice ◽

Data Set ◽

Learning Techniques ◽

Eeg Recordings ◽

The Given ◽

Close Interrelationship

In everyday clinical practice, there is an ongoing debate about the nature of major depressive disorder (MDD) in patients with borderline personality disorder (BPD). The underlying research does not give us a clear distinction between those 2 entities, although depression is among the most frequent comorbid diagnosis in borderline personality patients. The notion that depression can be a distinct disorder but also a symptom in other psychopathologies led our team to try and delineate those 2 entities using 146 EEG recordings and machine learning. The utilized algorithms, developed solely for this purpose, could not differentiate those 2 entities, meaning that patients suffering from MDD did not have significantly different EEG in terms of patients diagnosed with MDD and BPD respecting the given data and methods used. By increasing the data set and the spatiotemporal specificity, one could have a more sensitive diagnostic approach when using EEG recordings. To our knowledge, this is the first study that used EEG recordings and advanced machine learning techniques and further confirmed the close interrelationship between those 2 entities.

Download Full-text

Algorithmic fairness in credit scoring

Oxford Review of Economic Policy ◽

10.1093/oxrep/grab020 ◽

2021 ◽

Vol 37 (3) ◽

pp. 585-617

Author(s):

Teresa Bono ◽

Karen Croxson ◽

Adam Giles

Keyword(s):

Machine Learning ◽

Credit Scoring ◽

Large Data ◽

Error Rates ◽

The Past ◽

Ensemble Machine Learning ◽

Hidden Patterns ◽

Credit Scoring Model ◽

Distributional Impacts ◽

Modelling Approach

Abstract The use of machine learning as an input into decision-making is on the rise, owing to its ability to uncover hidden patterns in large data and improve prediction accuracy. Questions have been raised, however, about the potential distributional impacts of these technologies, with one concern being that they may perpetuate or even amplify human biases from the past. Exploiting detailed credit file data for 800,000 UK borrowers, we simulate a switch from a traditional (logit) credit scoring model to ensemble machine-learning methods. We confirm that machine-learning models are more accurate overall. We also find that they do as well as the simpler traditional model on relevant fairness criteria, where these criteria pertain to overall accuracy and error rates for population subgroups defined along protected or sensitive lines (gender, race, health status, and deprivation). We do observe some differences in the way credit-scoring models perform for different subgroups, but these manifest under a traditional modelling approach and switching to machine learning neither exacerbates nor eliminates these issues. The paper discusses some of the mechanical and data factors that may contribute to statistical fairness issues in the context of credit scoring.

Download Full-text

Using a Guided Machine Learning Ensemble Model to Predict Discharge Disposition following Meningioma Resection

Journal of Neurological Surgery Part B Skull Base ◽

10.1055/s-0037-1604393 ◽

2017 ◽

Vol 79 (02) ◽

pp. 123-130 ◽

Cited By ~ 4

Author(s):

Whitney Muhlestein ◽

Dallin Akagi ◽

Justiss Kallos ◽

Peter Morone ◽

Kyle Weaver ◽

...

Keyword(s):

Machine Learning ◽

Logistic Regression ◽

Patient Outcomes ◽

Predictive Power ◽

Univariate Analysis ◽

Area Under The Curve ◽

Motor Deficit ◽

Ensemble Model ◽

Algorithm Selection ◽

Discharge Disposition

Objective Machine learning (ML) algorithms are powerful tools for predicting patient outcomes. This study pilots a novel approach to algorithm selection and model creation using prediction of discharge disposition following meningioma resection as a proof of concept. Materials and Methods A diversity of ML algorithms were trained on a single-institution database of meningioma patients to predict discharge disposition. Algorithms were ranked by predictive power and top performers were combined to create an ensemble model. The final ensemble was internally validated on never-before-seen data to demonstrate generalizability. The predictive power of the ensemble was compared with a logistic regression. Further analyses were performed to identify how important variables impact the ensemble. Results Our ensemble model predicted disposition significantly better than a logistic regression (area under the curve of 0.78 and 0.71, respectively, p = 0.01). Tumor size, presentation at the emergency department, body mass index, convexity location, and preoperative motor deficit most strongly influence the model, though the independent impact of individual variables is nuanced. Conclusion Using a novel ML technique, we built a guided ML ensemble model that predicts discharge destination following meningioma resection with greater predictive power than a logistic regression, and that provides greater clinical insight than a univariate analysis. These techniques can be extended to predict many other patient outcomes of interest.

Download Full-text

Which reference class is evoked?

Behavioral and Brain Sciences ◽

10.1017/s0140525x00041364 ◽

1996 ◽

Vol 19 (1) ◽

pp. 34-35

Author(s):

Craig R. M. McKenzie ◽

Jack B. Soll

Keyword(s):

Search Space ◽

Reference Class ◽

Base Rates ◽

Reference Classes ◽

Choose People

AbstractAny instance (i.e., event, behavior, trait) belongs to infinitely many reference classes, hence there are infinitely many base rates from which to choose. People clearly do not entertain all possible reference classes, however, so something must be limiting the search space. We suggest some possible mechanisms that determine which reference class is evoked for the purpose of judgment and decision.

Download Full-text