A weighted random survival forest

Utkin, Lev V.; Konstantinov, Alexander A.; Chukanov, Viacheslav S.; Kots, Mikhail V.; Ryabinin, M. A.; Meldo, Anna A.

doi:10.48550/arxiv.1901.00213

Cited by 2 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The ML methods have several advantages over traditional statistical methods. These methods relax the assumption of linearity, handle the outliers efficiently, and handle the discrete variables or variables with large categories effectively; and fourth, allow for information extraction from large datasets (Breiman et al, 1984;Friedman et al, 1997b, Khatami et al, 2017Ahmad et al, 2018;Utkin et al, 2019). Bayesian Network is a well-known ML method that inherits the characteristics of ML and can determine the causal and associative relationships between variables.…”

Section: Methodologiesmentioning

confidence: 99%

Transport Assessment Using Bayesian Method to Determine Ride-Hailing in Kula Lumpur: A Case Study

Al Jarah

2023

jcoeng

View full text Add to dashboard Cite

This research was designed to investigate the factors affecting the frequency of use of ride-hailing in a fast-growing metropolitan region in Southeast Asia, Kuala Lumpur. An intercept survey was used to conduct this study in three potential locations that were acknowledged by one of the most famous ride-hailing companies in Kuala Lumpur. This study used non-parametric and machine learning techniques to analyze the data, including the Pearson chi-square test and Bayesian Network. From 38 statements (input variables), the Pearson chi-square test identified 14 variables as the most important. These variables were used as predictors in developing a BN model that predicts the probability of weekly usage frequency of ride-hailing. According to the final model, the attitude of the commuters towards the speed of ride-hailing over hailing regular taxis was the most important and presented in all probability conditions. Several related studies also identified ride-hailing speed as one of the top reasons for using this travel option. The findings of this study imply that commuters still compare the ride-hailing services with the traditional taxis in Kuala Lumpur, especially in terms of complementarity to other modes, ease of payment, ease of access, and speed. It is critical to have a sustainable strategy for keeping commuters’ satisfaction at the highest level because if the ride-hailing services cannot meet the commuters’ expectations, they may switch back to conventional transport options.

show abstract

Section: Methodologiesmentioning

confidence: 99%

Transport Assessment Using Bayesian Method to Determine Ride-Hailing in Kula Lumpur: A Case Study

Al Jarah

2023

jcoeng

View full text Add to dashboard Cite

show abstract

“…However, the assigned weights in the aforementioned works are not trainable parameters. Attempts to train weights of trees were carried out in [30,31,7,8], where weights are assigned by solving optimization problems, i.e., they incorporated into a certain loss function of the whole RF such that the loss function is minimized over values of weights.…”

Section: Related Workmentioning

confidence: 99%

Attention-based Random Forest and Contamination Model

Utkin¹,

Konstantinov²

2022

Preprint

Self Cite

View full text Add to dashboard Cite

A new approach called ABRF (the attention-based random forest) and its modifications for applying the attention mechanism to the random forest (RF) for regression and classification are proposed. The main idea behind the proposed ABRF models is to assign attention weights with trainable parameters to decision trees in a specific way. The weights depend on the distance between an instance, which falls into a corresponding leaf of a tree, and instances, which fall in the same leaf. This idea stems from representation of the Nadaraya-Watson kernel regression in the form of a RF. Three modifications of the general approach are proposed. The first one is based on applying the Huber's contamination model and on computing the attention weights by solving quadratic or linear optimization problems. The second and the third modifications use the gradient-based algorithms for computing trainable parameters. Numerical experiments with various regression and classification datasets illustrate the proposed method.

show abstract

A weighted random survival forest

Cited by 2 publications

References 0 publications

Transport Assessment Using Bayesian Method to Determine Ride-Hailing in Kula Lumpur: A Case Study

Transport Assessment Using Bayesian Method to Determine Ride-Hailing in Kula Lumpur: A Case Study

Attention-based Random Forest and Contamination Model

Contact Info

Product

Resources

About