Arabin Kumar Dey

Rahul Goswami, Arabin Kumar Dey

Recently Goswami et al. \cite{goswami2022concordance} introduced two novel implementations of combined regression strategy to find the conditional survival function. The paper uses regression-based weak learners and provides an alternative version of the combined regression strategy (COBRA) ensemble using the Integrated Brier Score to predict conditional survival function. We create a novel predictor based on a weighted version of all machine predictions taking weights as a specific function of normalized Integrated Brier Score. We use two different norms (Frobenius and Sup norm) to extract the proximity points in the algorithm. Our implementations consider right-censored data too. We illustrate the proposed algorithms through some real-life data analysis.

Rahul Goswami, Arabin Kumar Dey

In this paper, we predict conditional survival functions through a combined regression strategy. We take weak learners as different random survival trees. We propose to maximize concordance in the right-censored set up to find the optimal parameters. We explore two approaches, a usual survival cobra and a novel weighted predictor based on the concordance index. Our proposed formulations use two different norms, say, Max-norm and Frobenius norm, to find a proximity set of predictions from query points in the test dataset. We illustrate our algorithms through three different real-life dataset implementations.

Aryan Bhambu, Arabin Kumar Dey

In this paper we propose a novel procedure to construct a confidence interval for multivariate time series predictions using long short term memory network. The construction uses a few novel block bootstrap techniques. We also propose an innovative block length selection procedure for each of these schemes. Two novel benchmarks help us to compare the construction of this confidence intervals by different bootstrap techniques. We illustrate the whole construction through S\&P $500$ and Dow Jones Index datasets.

Aryan Bhambu, Arabin Kumar Dey

This research paper introduces innovative approaches for multivariate time series forecasting based on different variations of the combined regression strategy. We use specific data preprocessing techniques which makes a radical change in the behaviour of prediction. We compare the performance of the model based on two types of hyper-parameter tuning Bayesian optimisation (BO) and Usual Grid search. Our proposed methodologies outperform all state-of-the-art comparative models. We illustrate the methodologies through eight time series datasets from three categories: cryptocurrency, stock index, and short-term load forecasting.

Shankhyajyoti De, Arabin Kumar Dey, Deepak Gauda

In this paper, we show an innovative way to construct bootstrap confidence interval of a signal estimated based on a univariate LSTM model. We take three different types of bootstrap methods for dependent set up. We prescribe some useful suggestions to select the optimal block length while performing the bootstrapping of the sample. We also propose a benchmark to compare the confidence interval measured through different bootstrap strategies. We illustrate the experimental results through some stock price data set.

Arabin Kumar Dey, Himanshu Jhamb

In this article we select the unknown dimension of the feature by re- versible jump MCMC inside a simulated annealing in bayesian set up of collaborative filter. We implement the same in MovieLens small dataset. We also tune the hyper parameter by using a modified empirical bayes. It can also be used to guess an initial choice for hyper-parameters in grid search procedure even for the datasets where MCMC oscillates around the true value or takes long time to converge.

Arabin Kumar Dey, Suhas N., Talasila Sai Teja et al.

In this paper we describe a novel implementation of adaboost for prediction of survival function. We take different variations of the algorithm and compare the algorithms based on system run time and root mean square error. Our construction includes right censoring data and competing risk data too. We take different data set to illustrate the performance of the algorithms.

Arabin Kumar Dey, Raghav Somani, Sreangsu Acharyya

In this article we provide a formulation of empirical bayes described by Atchade (2011) to tune the hyperparameters of priors used in bayesian set up of collaborative filter. We implement the same in MovieLens small dataset. We see that it can be used to get a good initial choice for the parameters. It can also be used to guess an initial choice for hyper-parameters in grid search procedure even for the datasets where MCMC oscillates around the true value or takes long time to converge.