scholarly journals A Machine Learning Approach to Study the Relationship between Features of the Urban Environment and Street Value

Urban Science ◽  
2019 ◽  
Vol 3 (3) ◽  
pp. 100 ◽  
Author(s):  
Alessandro Venerandi ◽  
Giovanni Fusco ◽  
Andrea Tettamanzi ◽  
David Emsellem
Keyword(s):  
Machine Learning ◽  
Urban Environment ◽  
Future Research ◽  
Quantitative Methodology ◽  
Predictive Capacity ◽  
Spatial Unit ◽  
Quantitative Studies ◽  
Machine Learning Approach ◽  
The Relationship ◽  
French Riviera

Understanding what aspects of the urban environment are associated with better socioeconomic/liveability outcomes is a long standing research topic. Several quantitative studies have investigated such relationships. However, most of such works analysed single correlations, thus failing to obtain a more complete picture of how the urban environment can contribute to explain the observed phenomena. More recently, multivariate models have been suggested. However, they use a limited set of metrics, propose a coarse spatial unit of analysis, and assume linearity and independence among regressors. In this paper, we propose a quantitative methodology to study the relationship between a more comprehensive set of metrics of the urban environment and the valorisation of street segments that handles non-linearity and possible interactions among variables, through the use of Machine Learning (ML). The proposed methodology was tested on the French Riviera and outputs show a moderate predictive capacity (i.e., adjusted R 2 = 0.75 ) and insightful explanations on the nuanced relationships between selected features of the urban environment and street values. These findings are clearly location specific; however, the methodology is replicable and can thus inspire future research of this kind in different geographic contexts.

A Machine Learning Approach to Analyzing the Relationship Between Temperatures and Multi-Proxy Tree-Ring Records

2018 ◽  
Vol 74 (2) ◽  
pp. 210-224 ◽  
Author(s):  
Jernej Jevšenak ◽  
Sašo Džeroski ◽  
Saša Zavadlav ◽  
Tom Levanič
Keyword(s):  
Machine Learning ◽  
Tree Ring ◽  
Learning Approach ◽  
Machine Learning Approach ◽  
The Relationship

scholarly journals COVID-19 Pandemic Prediction for Hungary; a Hybrid Machine Learning Approach

2020 ◽  
Author(s):  
Amir Mosavi
Keyword(s):  
Machine Learning ◽  
Prediction Models ◽  
Future Research ◽  
Complex Nature ◽  
Learning Approach ◽  
Epidemiological Models ◽  
Inference System ◽  
Proper Actions ◽  
Machine Learning Approach ◽  
Hybrid Machine

Several epidemiological models are being used around the world to project the number of infected individuals and the mortality rates of the COVID-19 outbreak. Advancing accurate prediction models is of utmost importance to take proper actions. Due to a high level of uncertainty or even lack of essential data, the standard epidemiological models have been challenged regarding the delivery of higher accuracy for long-term prediction. As an alternative to the susceptible-infected-resistant (SIR)-based models, this study proposes a hybrid machine learning approach to predict the COVID-19 and we exemplify its potential using data from Hungary. The hybrid machine learning methods of adaptive network-based fuzzy inference system (ANFIS) and multi-layered perceptron-imperialist competitive algorithm (MLP-ICA) are used to predict time series of infected individuals and mortality rate. The models predict that by late May, the outbreak and the total morality will drop substantially. The validation is performed for nine days with promising results, which confirms the model accuracy. It is expected that the model maintains its accuracy as long as no significant interruption occurs. Based on the results reported here, and due to the complex nature of the COVID-19 outbreak and variation in its behavior from nation-to-nation, this study suggests machine learning as an effective tool to model the outbreak. This paper provides an initial benchmarking to demonstrate the potential of machine learning for future research.

Conclusion: Clemency’s Place

2019 ◽  
pp. 226-252
Author(s):  
Daniel Pascoe
Keyword(s):  
Criminal Justice ◽  
Research Agenda ◽  
Southeast Asian ◽  
Future Research ◽  
Future Research Agenda ◽  
Quantitative Studies ◽  
Capital Cases ◽  
Judicial Sanctions ◽  
The Impact ◽  
The Relationship

The Conclusion, after briefly summarizing the respective country positions and restating the three-part hypothesis outlined in Chapter 7, considers what Southeast Asia’s ‘natural experiment’ on clemency means for policymakers, NGO staff, and legal practitioners working on death penalty cases in the region. The four national case studies, together with Chapter 7’s comparative hypothesis, suggest various practical means of boosting each Southeast Asian jurisdiction’s clemency rate within finalized capital cases. The Conclusion also considers what implications the comparative findings outlined in Chapter 7 have for the broader criminal justice literature in other parts of the world (particularly concerning the relationship between discretion exercised at different stages of a criminal case, the relationship between extrajudicial and judicial sanctions, the impact of democratization on criminal justice policies, and the influence of delay on criminal justice decision-making). Finally, the Conclusion suggests a future research agenda, including quantitative studies to ‘test’ the accuracy of the book’s three-part hypothesis in other parts of the retentionist world. The chapter ends with several predictions regarding the future of capital clemency in the four Southeast Asian jurisdictions under analysis (Thailand, Singapore, Malaysia, and Indonesia).

scholarly journals Modeling of apartment prices in a Colombian context from a machine learning approach with stable-important attributes

DYNA ◽  
2020 ◽  
Vol 87 (212) ◽  
pp. 63-72
Author(s):  
Jorge Iván Pérez Rave ◽  
Favián González Echavarría ◽  
Juan Carlos Correa Morales
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Learning Approach ◽  
Predictive Capability ◽  
Predictive Capacity ◽  
Machine Learning Model ◽  
Machine Learning Approach ◽  
Property Price ◽  
Object Of Study ◽  
Online Pricing

The objective of this work is to develop a machine learning model for online pricing of apartments in a Colombian context. This article addresses three aspects: i) it compares the predictive capacity of linear regression, regression trees, random forest and bagging; ii) it studies the effect of a group of text attributes on the predictive capability of the models; and iii) it identifies the more stable-important attributes and interprets them from an inferential perspective to better understand the object of study. The sample consists of 15,177 observations of real estate. The methods of assembly (random forest and bagging) show predictive superiority with respect to others. The attributes derived from the text had a significant relationship with the property price (on a log scale). However, their contribution to the predictive capacity was almost nil, since four different attributes achieved highly accurate predictions and remained stable when the sample change.

Leadership and corporate responsibility: a review of the empirical evidence

2015 ◽  
Vol 1 (1) ◽  
pp. 76-107 ◽  
Author(s):  
Daina Mazutis ◽  
Christopher Zintel
Keyword(s):  
Empirical Evidence ◽  
Corporate Responsibility ◽  
Current Knowledge ◽  
Narrative Review ◽  
Integrative Model ◽  
Future Research ◽  
Moderating Effects ◽  
Content Type ◽  
Quantitative Studies ◽  
The Relationship

Purpose – The purpose of this paper is to consolidate the state of the empirical research to date on the relationship between leadership and corporate responsibility. Design/methodology/approach – The authors conduct a comprehensive, systematic and narrative review of all published quantitative studies that have examined the link between leadership and corporate responsibility broadly defined, and the authors put forward an integrative model encapsulating current knowledge in this domain. Findings – The authors not only identify validated direct, indirect and moderating effects of leadership on corporate responsibility but also point to gaps in the literature that imply important directions for further research. Originality/value – The authors aim to make the following contributions to both the leadership and the corporate responsibility literatures. First, the systematic and narrative review in and of itself provides an important consolidation of existing knowledge in both domains. Second, the authors confirm that the preponderance of empirical evidence supports that leadership matters to corporate responsibility efforts in organizations. Lastly, the review provides a comprehensive model of the relationship between leadership and corporate responsibility that has important implications for future research and theory building in this field.

scholarly journals A Novel Ensemble Machine Learning Approach for Bioarchaeological Sex Prediction

Technologies ◽  
2021 ◽  
Vol 9 (2) ◽  
pp. 23
Author(s):  
Evan Muzzall
Keyword(s):  
Machine Learning ◽  
Missing Data ◽  
Central Italy ◽  
Area Under The Curve ◽  
Machine Learning Algorithms ◽  
Low Rank ◽  
Future Research ◽  
Learning Approach ◽  
Machine Learning Approach ◽  
Metric Distances

I present a novel machine learning approach to predict sex in the bioarchaeological record. Eighteen cranial interlandmark distances and five maxillary dental metric distances were recorded from n = 420 human skeletons from the necropolises at Alfedena (600–400 BCE) and Campovalano (750–200 BCE and 9–11th Centuries CE) in central Italy. A generalized low rank model (GLRM) was used to impute missing data and Area under the Curve—Receiver Operating Characteristic (AUC-ROC) with 20-fold stratified cross-validation was used to evaluate predictive performance of eight machine learning algorithms on different subsets of the data. Additional perspectives such as this one show strong potential for sex prediction in bioarchaeological and forensic anthropological contexts. Furthermore, GLRMs have the potential to handle missing data in ways previously unexplored in the discipline. Although results of this study look promising (highest AUC-ROC = 0.9722 for predicting binary male/female sex), the main limitation is that the sexes of the individuals included were not known but were estimated using standard macroscopic bioarchaeological methods. However, future research should apply this machine learning approach to known-sex reference samples in order to better understand its value, along with the more general contributions that machine learning can make to the reconstruction of past human lifeways.

scholarly journals Predictive Modeling of Psychiatric Illness using Electronic Health Records and a Novel Machine Learning Approach with Artificial Intelligence

2020 ◽  
Author(s):  
Matthew David Nemesure ◽  
Michael Heinz ◽  
Raphael Huang ◽  
Nicholas C. Jacobson
Keyword(s):  
Machine Learning ◽  
Undergraduate Students ◽  
General Health ◽  
Patient Characteristics ◽  
Future Research ◽  
Learning Methods ◽  
Machine Learning Methods ◽  
Primary Care Settings ◽  
Machine Learning Approach ◽  
Shapley Values

Background: Generalized anxiety disorder (GAD) and major depressive disorder (MDD) are highly prevalent and impairing problems, but frequently go undetected, leading to substantial treatment delays. Electronic medical records (EMRs) collect a great deal of biometric markers and patient characteristics that could foster the detection of GAD and MDD in primary care settings. Methods: We approach the problem of predicting MDD and GAD using a novel machine learning pipeline. The pipeline constitutes an ensemble of algorithmically distinct machine learning methods, including deep learning. A sample of 4,184 undergraduate students completed the study, undergoing a general health screening and completing a psychiatric assessment for MDD and GAD. Using 59 biomedical and demographic features from the general health survey and an additional set of engineered features, we trained the model to predict GAD and MDD. Results: We assessed the model's performance on a held-out test set and found an AUC of 0.72 and 0.66 for GAD, and MDD, respectively. Additionally, we used advanced techniques (Shapley values) to illuminate which features had the greatest impact on prediction for each disease. The top predictive features for MDD were “difficulty memorizing lessons”, “financial difficulties” and “alcohol consumption”. The top predictive features for GAD were the necessity for a control examination, being overweight/obese, and irregular meal consumption. Conclusions: Our results indicate a successful application of machine learning methods in detection of GAD and MDD based on EMR-like data. By identifying biomarkers of GAD and MDD, these results may be used in future research to aid in the early detection of MDD and GAD.

Sign in / Sign up

Export Citation Format

Share Document