Rafat Ashraf Joy

Rafat Ashraf Joy

Publications

TriOpt: A Scalable Algorithm for Linear Causal Discovery

Published in arXiv, 2026

Learning causal relations from observational data is challenging because the graph search space grows super-exponentially with the number of variables. TriOpt integrates ordering-based and continuous optimization approaches into two efficient stages: fast topological ordering estimation using the Sherman-Morrison rank-1 downdate and additive linear kernels, followed by convex structure learning without an acyclicity constraint. Under the true ordering, TriOpt exactly recovers the underlying linear DAG, while experiments on synthetic, semi-synthetic, and real-world datasets demonstrate orders-of-magnitude speedups with comparable or superior accuracy.

Recommended citation: @article{Joy2026TriOpt, author = {Joy, Rafat Ashraf and Zheleva, Elena}, title = {{TriOpt: A Scalable Algorithm for Linear Causal Discovery}}, journal = {arXiv preprint arXiv:2605.17465}, year = {2026}, month = {May}, doi = {10.48550/arXiv.2605.17465} } [https://arxiv.org/abs/2605.17465](https://arxiv.org/abs/2605.17465)

Fine Tuning the Prediction of the Compressive Strength of Concrete : A Bayesian Optimization Based Approach

Published in IEEE Xplore, 2021

This study demonstrates the efficacy of Bayesian Optimization to improve the performance of machine learning models for predicting the strength properties of concrete specimens. In the first phase of the study, five machine learning models(SVR, ABR, RFR, GBR and KNN Regressor) were compared on the basis of rmse, mae and r-squared value on the test set. Two best performing models(GBR and RFR) were selected among the five models for further improvement. In the second phase, hyperparameter tuning by Bayesian Optimization method was done on these two models. Experimental results testify that Bayesian Optimization on these two models improved their prediction performance further.

Recommended citation: @incollection{Joy2021Aug, author = {Joy, Rafat Ashraf}, title = {{Fine Tuning the Prediction of the Compressive Strength of Concrete : A Bayesian Optimization Based Approach}}, booktitle = {{2021 International Conference on INnovations in Intelligent SysTems and Applications (INISTA)}}, journal = {2021 International Conference on INnovations in Intelligent SysTems and Applications (INISTA)}, pages = {1--6}, year = {2021}, month = {Aug}, publisher = {IEEE}, doi = {10.1109/INISTA52262.2021.9548593} } https://ieeexplore.ieee.org/document/9548593

An Interpretable Catboost Model to Predict the Power of Combined Cycle Power Plants

Published in IEEE Xplore, 2021

In this study, a Catboost model which can predict the electrical energy output (EP) of a combined cycle power plant is presented. The Root Mean Square Error (RMSE) value achieved with the Catboost model is 0.0678, that is outstandingly lower in comparison with other methods in existing literature. Finally, Shapley additive explanations (SHAP) were employed to explain the inner workings of the Catboost model

Recommended citation: @incollection{Joy2021Jul, author = {Joy, Rafat Ashraf}, title = {{An Interpretable Catboost Model to Predict the Power of Combined Cycle Power Plants}}, booktitle = {{2021 International Conference on Information Technology (ICIT)}}, journal = {2021 International Conference on Information Technology (ICIT)}, pages = {435--439}, year = {2021}, month = {Jul}, publisher = {IEEE}, doi = {10.1109/ICIT52682.2021.9491700} } https://ieeexplore.ieee.org/document/9491700