no code implementations • 5 Sep 2023 • Linwei Hu, Soroush Aramideh, Jie Chen, Vijayan N. Nair
It is straightforward to fit a monotone model to $f(x)$ using the options in XGBoost.
no code implementations • 18 Aug 2023 • Mohammad Ahmadi Achachlouei, Omkar Patil, Tarun Joshi, Vijayan N. Nair
This paper surveys the current state of the art in document automation (DA).
no code implementations • 25 May 2023 • Linwei Hu, Vijayan N. Nair, Agus Sudjianto, Aijun Zhang, Jie Chen
To understand and explain the model results, one had to rely on post hoc explainability techniques, which are known to have limitations.
no code implementations • 15 Nov 2022 • Anwesha Bhattacharyya, Joel Vaughan, Vijayan N. Nair
Hyper-parameters (HPs) are an important part of machine learning (ML) model development and can greatly influence performance.
no code implementations • 12 Aug 2022 • Tianshu Feng, Zhipu Zhou, Joshi Tarun, Vijayan N. Nair
There are many different methods in the literature for local explanation of machine learning results.
no code implementations • 14 Jul 2022 • Linwei Hu, Jie Chen, Vijayan N. Nair
We propose a new algorithm, called GAMI-Tree, that is similar to EBM, but has a number of features that lead to better performance.
no code implementations • 24 Jun 2022 • Soham Raste, Rahul Singh, Joel Vaughan, Vijayan N. Nair
Among the different algorithms, randomness in model training causes larger variation for FFNNs compared to tree-based methods.
no code implementations • 23 May 2022 • Tianjie Wang, Jie Chen, Joel Vaughan, Vijayan N. Nair
Regression problems with time-series predictors are common in banking and many other areas of application.
no code implementations • 27 Apr 2022 • Alice J. Liu, Arpita Mukherjee, Linwei Hu, Jie Chen, Vijayan N. Nair
Overall, XGB and FFNNs were competitive, with FFNNs showing better performance in smooth models and tree-based boosting algorithms performing better in non-smooth models.
no code implementations • 26 Apr 2022 • Vijayan N. Nair, Tianshu Feng, Linwei Hu, Zach Zhang, Jie Chen, Agus Sudjianto
The applicant is then entitled to an explanation for the negative decision.
no code implementations • 23 Sep 2021 • Mohammad Ahmadi Achachlouei, Omkar Patil, Tarun Joshi, Vijayan N. Nair
This paper surveys the current state of the art in document automation (DA).
no code implementations • 18 May 2021 • Wei Zhao, Rahul Singh, Tarun Joshi, Agus Sudjianto, Vijayan N. Nair
We also study the impact of the complexity of the convolutional layers and the classification layers on the model performance.
no code implementations • 13 May 2021 • Nengfeng Zhou, Zach Zhang, Vijayan N. Nair, Harsh Singhal, Jie Chen, Agus Sudjianto
In this paper, we provide an overview of bias and fairness issues that arise with the use of ML algorithms.
no code implementations • 4 Sep 2020 • Mina Naghshnejad, Tarun Joshi, Vijayan N. Nair
Additionally, we discuss different techniques to improve the performance of these models at each stage of the pipeline.
no code implementations • 26 Aug 2020 • Wei Zhao, Tarun Joshi, Vijayan N. Nair, Agus Sudjianto
Deep neural networks are increasingly used in natural language processing (NLP) models.
no code implementations • 12 Aug 2020 • Rahul Singh, Tarun Joshi, Vijayan N. Nair, Agus Sudjianto
We propose algorithms to create adversarial attacks to assess model robustness in text classification problems.
no code implementations • 28 Jul 2020 • Linwei Hu, Jie Chen, Vijayan N. Nair, Agus Sudjianto
Supervised Machine Learning (SML) algorithms, such as Gradient Boosting, Random Forest, and Neural Networks, have become popular in recent years due to their superior predictive performance over traditional statistical methods.
no code implementations • 28 Jul 2020 • Linwei Hu, Jie Chen, Joel Vaughan, Hanyu Yang, Kelly Wang, Agus Sudjianto, Vijayan N. Nair
This article provides an overview of Supervised Machine Learning (SML) with a focus on applications to banking.
no code implementations • 5 Apr 2020 • Jie Chen, Joel Vaughan, Vijayan N. Nair, Agus Sudjianto
While machine learning techniques have been successfully applied in several fields, the black-box nature of the models presents challenges for interpreting and explaining the results.
no code implementations • 5 Jun 2018 • Joel Vaughan, Agus Sudjianto, Erind Brahimi, Jie Chen, Vijayan N. Nair
In this paper, we present the Explainable Neural Network (xNN), a structured neural network designed especially to learn interpretable features.
no code implementations • 2 Jun 2018 • Linwei Hu, Jie Chen, Vijayan N. Nair, Agus Sudjianto
This is in contrast with the KLIME approach that is based on clustering the predictor space.