Publications

Survival regression is used to estimate the relation between time-to-event and feature variables, and is important in application domains such as medicine, marketing, risk management and sales management. Nonlinear tree based machine learning algorithms as implemented in libraries such as XGBoost, scikit-learn, LightGBM, and CatBoost are often more accurate in practice than linear models. However, existing implementations of tree-based models have offered limited support for survival regression. In this work, we propose and implement loss functions for learning accelerated failure time (AFT) models in XGBoost, to increase the support for survival modeling for different kinds of label censoring. The AFT model assumes effects that directly accelerate or decelerate the survival time for different kinds of censored data sets. We demonstrate with real and simulated experiments the effectiveness of AFT in XGBoost with respect to a number of baselines, in two respects: generalization performance and training speed. Furthermore, we take advantage of the support for NVIDIA GPUs in XGBoost to achieve substantial speedup over multi-coreCPUs. To our knowledge, our work is the first implementation of AFT that utilizes the processing power of NVIDIA GPUs.

Predicting the direction of assets have been an active area of study and difficult task. Machine learning models have been used to build robust models to model the above task. Ensemble methods are one of them resulting better than single supervised method. We have used generative and discriminative classifiers to create the stack, particularly 3 generative and 6 discriminative classifiers and optimized over one-layer Neural Network to model the direction of price cryptocurrencies. Features used are technical indicators not limited to trend, momentum, volume, volatility indicators and sentiment indicators. For Cross validation, Purged Walk forward cross validation has been used. In terms of accuracy, we have done comparative analysis of the performance of Ensemble method with Stacking and individual models. We have also developed methodology for features importance for stacked model. Important indicators are identified based on feature importance.

Survival month for non-small lung cancer patients depend upon which stage of lung cancer is present. Our aim is to identify smoking specific gene expression biomarkers in prognosis of lung cancer patients. In this paper, we introduce the network elastic net, a generalization of network lasso that allows for simultaneous clustering and regression on graphs. In network elastic net, we consider similar patients based on smoking cigarettes per year to form the network. We then further find the suitable cluster among patients based on coefficients of genes having different survival month structures and showed the efficacy of the clusters using stage enrichment. This can be used to identify the stage of cancer using gene expression and smoking behavior of patients without doing any tests.

The linear ballistic accumulator model is a theory of decision-making that has been used to analyse data from human and animal experiments. It represents decisions as a race between independent evidence accumulators, and has proven successful in a form assuming a normal distribution for accumulation (“drift”) rates. However, this assumption has some limitations, including the corollary that some decision times are negative or undefined. We show that various drift rate distributions with strictly positive support can be substituted for the normal distribution without loss of analytic tractability, provided the candidate distribution has a closed-form expression for its mean when truncated to a closed interval. We illustrate the approach by developing three new linear ballistic accumulation variants, in which the normal distribution for drift rates is replaced by either the lognormal, Fréchet, or gamma distribution. We compare some properties of these new variants to the original normal-rate model.