Estimating conditional average treatment effects (CATEs) from observational data is relevant in many fields such as personalized medicine. However, in practice, the treatment assignment is usually confounded by unobserved variables and thus introduces bias. A remedy to remove the bias is the use of instrumental variables (IVs). Such settings are widespread in medicine (e.g., trials where the treatment assignment is used as binary IV). In this paper, we propose a novel, multiply robust machine learning framework, called MRIV, for estimating CATEs using binary IVs and thus yield an unbiased CATE estimator. Different from previous work for binary IVs, our framework estimates the CATE directly via a pseudo outcome regression. Across various computational experiments, we demonstrate empirically that our MRIV-Net achieves state-of-theart performance. To the best of our knowledge, our MRIV is the first multiply robust machine learning framework tailored to estimating CATEs in the binary IV setting. Conditional average treatment effects (CATEs) are relevant across many disciplines such as marketing (Varian, 2016) and personalized medicine (Yazdani & Boerwinkle, 2015). Knowledge about CATEs provides insights into the heterogeneity of treatment effects, and thus helps in making potentially better treatment decisions (Frauen et al., 2023). Many recent works that use machine learning to estimate causal effects, in particular CATEs, are based on the assumption of unconfoundedness (Alaa & van der Schaar, 2017; Lim et al., 2018; Melnychuk et al., 2022a;b). In practice, however, this assumption is often violated because it is common that some confounders are not reported in the data. Typical examples are income or the socioeconomic status of patients, which are not stored in medical files. If the confounding is sufficiently strong, standard methods for estimating CATEs suffer from confounding bias (Pearl, 2009), which may lead to inferior treatment decisions. To handle unobserved confounders, instrumental variables (IVs) can be leveraged to relax the assumption of unconfoundedness and still compute reliable CATE estimates. IV methods were originally developed in economics (Wright, 1928), but, only recently, there is a growing interest in combining IV methods with machine learning (see Sec. 3). Importantly, IV methods outperform classical CATE estimators if a sufficient amount of confounding is not observed (Hartford et al., 2017).

The challenges in applications of solar energy lies in its intermittency and dependency on meteorological parameters such as; solar radiation, ambient temperature, rainfall, wind-speed etc., and many other physical parameters like dust accumulation etc. Hence, it is important to estimate the amount of solar photovoltaic (PV) power generation for a specific geographical location. Machine learning (ML) models have gained importance and are widely used for prediction of solar power plant performance. In this paper, the impact of weather parameters on solar PV power generation is estimated by several Ensemble ML (EML) models like Bagging, Boosting, Stacking, and Voting for the first time. The performance of chosen ML algorithms is validated by field dataset of a 10kWp solar PV power plant in Eastern India region. Furthermore, a complete test-bed framework has been designed for data mining as well as to select appropriate learning models. It also supports feature selection and reduction for dataset to reduce space and time complexity of the learning models. The results demonstrate greater prediction accuracy of around 96% for Stacking and Voting EML models. The proposed work is a generalized one and can be very useful for predicting the performance of large-scale solar PV power plants also.

This paper presents a model-agnostic ensemble approach for supervised learning. The proposed approach is based on a parametric version of Random Subspace, in which each base model is learned from a feature subset sampled according to a Bernoulli distribution. Parameter optimization is performed using gradient descent and is rendered tractable by using an importance sampling approach that circumvents frequent re-training of the base models after each gradient descent step. The degree of randomization in our parametric Random Subspace is thus automatically tuned through the optimization of the feature selection probabilities. This is an advantage over the standard Random Subspace approach, where the degree of randomization is controlled by a hyper-parameter. Furthermore, the optimized feature selection probabilities can be interpreted as feature importance scores. Our algorithm can also easily incorporate any differentiable regularization term to impose constraints on these importance scores.

This dissertation focuses on modern causal inference under uncertainty and data restrictions, with applications to neoadjuvant clinical trials, distributed data networks, and robust individualized decision making. In the first project, we propose a method under the principal stratification framework to identify and estimate the average treatment effects on a binary outcome, conditional on the counterfactual status of a post-treatment intermediate response. Under mild assumptions, the treatment effect of interest can be identified. We extend the approach to address censored outcome data. The proposed method is applied to a neoadjuvant clinical trial and its performance is evaluated via simulation studies. In the second project, we propose a tree-based model averaging approach to improve the estimation accuracy of conditional average treatment effects at a target site by leveraging models derived from other potentially heterogeneous sites, without them sharing subject-level data. The performance of this approach is demonstrated by a study of the causal effects of oxygen therapy on hospital survival rates and backed up by comprehensive simulations. In the third project, we propose a robust individualized decision learning framework with sensitive variables to improve the worst-case outcomes of individuals caused by sensitive variables that are unavailable at the time of decision. Unlike most existing work that uses mean-optimal objectives, we propose a robust learning framework by finding a newly defined quantile- or infimum-optimal decision rule. From a causal perspective, we also generalize the classic notion of (average) fairness to conditional fairness for individual subjects. The reliable performance of the proposed method is demonstrated through synthetic experiments and three real-data applications.

In this paper, I try to tame "Basu's elephants" (data with extreme selection on observables). I propose new practical large-sample and finite-sample methods for estimating and inferring heterogeneous causal effects (under unconfoundedness) in the empirically relevant context of limited overlap. I develop a general principle called "Stable Probability Weighting" (SPW) that can be used as an alternative to the widely used Inverse Probability Weighting (IPW) technique, which relies on strong overlap. I show that IPW (or its augmented version), when valid, is a special case of the more general SPW (or its doubly robust version), which adjusts for the extremeness of the conditional probabilities of the treatment states. The SPW principle can be implemented using several existing large-sample parametric, semiparametric, and nonparametric procedures for conditional moment models. In addition, I provide new finite-sample results that apply when unconfoundedness is plausible within fine strata. Since IPW estimation relies on the problematic reciprocal of the estimated propensity score, I develop a "Finite-Sample Stable Probability Weighting" (FPW) set-estimator that is unbiased in a sense. I also propose new finite-sample inference methods for testing a general class of weak null hypotheses. The associated computationally convenient methods, which can be used to construct valid confidence sets and to bound the finite-sample confidence distribution, are of independent interest. My large-sample and finite-sample frameworks extend to the setting of multivalued treatments.

Reinforcement learning (RL) has been widely used in text generation to alleviate the exposure bias issue or to utilize non-parallel datasets. The reward function plays an important role in making RL training successful. However, previous reward functions are typically task-specific and sparse, restricting the use of RL. In our work, we propose a task-agnostic approach that derives a step-wise reward function directly from a model trained with teacher forcing. We additionally propose a simple modification to stabilize the RL training on non-parallel datasets with our induced reward function. Empirical results show that our method outperforms self-training and reward regression methods on several text generation tasks, confirming the effectiveness of our reward function.

Understanding the dynamics of financial transactions among people is critically important for various applications such as fraud detection. One important aspect of financial transaction networks is temporality. The order and repetition of transactions can offer new insights when considered within the graph structure. Temporal motifs, defined as a set of nodes that interact with each other in a short time period, are a promising tool in this context. In this work, we study three unique temporal financial networks: transactions in Mercari, an online marketplace, payments in a synthetic network generated by J.P. Morgan Chase, and payments and friendships among Venmo users. We consider the fraud detection problem on the Mercari and J.P. Morgan Chase networks, for which the ground truth is available. We show that temporal motifs offer superior performance than a previous method that considers simple graph features. For the Venmo network, we investigate the interplay between financial and social relations on three tasks: friendship prediction, vendor identification, and analysis of temporal cycles. For friendship prediction, temporal motifs yield better results than general heuristics, such as Jaccard and Adamic-Adar measures. We are also able to identify vendors with high accuracy and observe interesting patterns in rare motifs, like temporal cycles. We believe that the analysis, datasets, and lessons from this work will be beneficial for future research on financial transaction networks.

Linear regression is when linear predictors (or independent variables) are used to predict a dependent variable. In this case, y is the dependent variable and x is the independent variable (c is a constant). The goal of a linear regression model is to determine the best coefficient (a in the example above) for x to most accurately predict y. Now let's generalize that example, which is also known as mulitple linear regression. In a multiple linear regression model, the goal is to find the line of best fit that describes the relationship between the dependent variable and multiple independent variables.

Relating a set of variables X to a response y is crucial in chemometrics. A quantitative prediction objective can be enriched by qualitative data interpretation, for instance by locating the most influential features. When high-dimensional problems arise, dimension reduction techniques can be used. Most notable are projections (e.g. Partial Least Squares or PLS ) or variable selections (e.g. lasso). Sparse partial least squares combine both strategies, by blending variable selection into PLS. The variant presented in this paper, Dual-sPLS, generalizes the classical PLS1 algorithm. It provides balance between accurate prediction and efficient interpretation. It is based on penalizations inspired by classical regression methods (lasso, group lasso, least squares, ridge) and uses the dual norm notion. The resulting sparsity is enforced by an intuitive shrinking ratio parameter. Dual-sPLS favorably compares to similar regression methods, on simulated and real chemical data. Code is provided as an open-source package in R: \url{https://CRAN.R-project.org/package=dual.spls}.

Artificial Intelligence is being employed by humans to collaboratively solve complicated tasks for search and rescue, manufacturing, etc. Efficient teamwork can be achieved by understanding user preferences and recommending different strategies for solving the particular task to humans. Prior work has focused on personalization of recommendation systems for relatively well-understood tasks in the context of e-commerce or social networks. In this paper, we seek to understand the important factors to consider while designing user-centric strategy recommendation systems for decision-making. We conducted a human-subjects experiment (n=60) for measuring the preferences of users with different personality types towards different strategy recommendation systems. We conducted our experiment across four types of strategy recommendation modalities that have been established in prior work: (1) Single strategy recommendation, (2) Multiple similar recommendations, (3) Multiple diverse recommendations, (4) All possible strategies recommendations. While these strategy recommendation schemes have been explored independently in prior work, our study is novel in that we employ all of them simultaneously and in the context of strategy recommendations, to provide us an in-depth overview of the perception of different strategy recommendation systems. We found that certain personality traits, such as conscientiousness, notably impact the preference towards a particular type of system (p < 0.01). Finally, we report an interesting relationship between usability, alignment and perceived intelligence wherein greater perceived alignment of recommendations with one's own preferences leads to higher perceived intelligence (p < 0.01) and higher usability (p < 0.01).