Crop residue burning is a major source of air pollution in many parts of the world, notably South Asia. Policymakers, practitioners and researchers have invested in both measuring impacts and developing interventions to reduce burning. However, measuring the impacts of burning or the effectiveness of interventions to reduce burning requires data on where burning occurred. These data are challenging to collect in the field, both in terms of cost and feasibility. We take advantage of data from ground-based monitoring of crop residue burning in Punjab, India to explore whether burning can be detected more effectively using accessible satellite imagery. Specifically, we used 3m PlanetScope data with high temporal resolution (up to daily) as well as publicly-available Sentinel-2 data with weekly temporal resolution but greater depth of spectral information. Following an analysis of the ability of different spectral bands and burn indices to separate burned and unburned plots individually, we built a Random Forest model with those determined to provide the greatest separability and evaluated model performance with ground-verified data. Our overall model accuracy of 82-percent is favorable given the challenges presented by the measurement. Based on insights from this process, we discuss technical challenges of detecting crop residue burning from satellite imagery as well as challenges to measuring impacts, both of burning and of policy interventions.

Given thousands of equally accurate machine learning (ML) models, how can users choose among them? A recent ML technique enables domain experts and data scientists to generate a complete Rashomon set for sparse decision trees--a huge set of almost-optimal interpretable ML models. To help ML practitioners identify models with desirable properties from this Rashomon set, we develop TimberTrek, the first interactive visualization system that summarizes thousands of sparse decision trees at scale. Two usage scenarios highlight how TimberTrek can empower users to easily explore, compare, and curate models that align with their domain knowledge and values. Our open-source tool runs directly in users' computational notebooks and web browsers, lowering the barrier to creating more responsible ML models. TimberTrek is available at the following public demo link: https://poloclub.github.io/timbertrek.

We present Multiple Scenario Verifiable Reinforcement Learning via Policy Extraction (MSVIPER), a new method for policy distillation to decision trees for improved robot navigation. MSVIPER learns an "expert" policy using any Reinforcement Learning (RL) technique involving learning a state-action mapping and then uses imitation learning to learn a decision-tree policy from it. We demonstrate that MSVIPER results in efficient decision trees and can accurately mimic the behavior of the expert policy. Moreover, we present efficient policy distillation and tree-modification techniques that take advantage of the decision tree structure to allow improvements to a policy without retraining. We use our approach to improve the performance of RL-based robot navigation algorithms for indoor and outdoor scenes. We demonstrate the benefits in terms of reduced freezing and oscillation behaviors (by up to 95\% reduction) for mobile robots navigating among dynamic obstacles and reduced vibrations and oscillation (by up to 17\%) for outdoor robot navigation on complex, uneven terrains.

Fairness testing aims at mitigating unintended discrimination in the decision-making process of data-driven AI systems. Individual discrimination may occur when an AI model makes different decisions for two distinct individuals who are distinguishable solely according to protected attributes, such as age and race. Such instances reveal biased AI behaviour, and are called Individual Discriminatory Instances (IDIs). In this paper, we propose an approach for the selection of the initial seeds to generate IDIs for fairness testing. Previous studies mainly used random initial seeds to this end. However this phase is crucial, as these seeds are the basis of the follow-up IDIs generation. We dubbed our proposed seed selection approach I&D. It generates a large number of initial IDIs exhibiting a great diversity, aiming at improving the overall performance of fairness testing. Our empirical study reveal that I&D is able to produce a larger number of IDIs with respect to four state-of-the-art seed generation approaches, generating 1.68X more IDIs on average. Moreover, we compare the use of I&D to train machine learning models and find that using I&D reduces the number of remaining IDIs by 29% when compared to the state-of-the-art, thus indicating that I&D is effective for improving model fairness

Class imbalance poses a major challenge for machine learning as most supervised learning models might exhibit bias towards the majority class and under-perform in the minority class. Cost-sensitive learning tackles this problem by treating the classes differently, formulated typically via a user-defined fixed misclassification cost matrix provided as input to the learner. Such parameter tuning is a challenging task that requires domain knowledge and moreover, wrong adjustments might lead to overall predictive performance deterioration. In this work, we propose a novel cost-sensitive boosting approach for imbalanced data that dynamically adjusts the misclassification costs over the boosting rounds in response to model's performance instead of using a fixed misclassification cost matrix. Our method, called AdaCC, is parameter-free as it relies on the cumulative behavior of the boosting model in order to adjust the misclassification costs for the next boosting round and comes with theoretical guarantees regarding the training error. Experiments on 27 real-world datasets from different domains with high class imbalance demonstrate the superiority of our method over 12 state-of-the-art cost-sensitive boosting approaches exhibiting consistent improvements in different measures, for instance, in the range of [0.3%-28.56%] for AUC, [3.4%-21.4%] for balanced accuracy, [4.8%-45%] for gmean and [7.4%-85.5%] for recall.

When discussing classifiers, decision trees are often thought of as easily interpretable models when compared to numerous more complex classifiers, especially those of the blackbox variety. And this is generally true. This is especially true of rather comparatively simple models created from simple data. This is much-less true of complex decision trees crafted from large amounts of (high-dimensional) data. Even otherwise straightforward decision trees which are of great depth and/or breadth, consisting of heavy branching, can be difficult to trace.

This study investigates the impact of machine learning models on the generation of counterfactual explanations by conducting a benchmark evaluation over three different types of models: decision-tree (fully transparent, interpretable, white-box model), a random forest (a semi-interpretable, grey-box model), and a neural network (a fully opaque, black-box model). We tested the counterfactual generation process using four algorithms (DiCE, WatcherCF, prototype, and GrowingSpheresCF) in the literature in five different datasets (COMPAS, Adult, German, Diabetes, and Breast Cancer). Our findings indicate that: (1) Different machine learning models have no impact on the generation of counterfactual explanations; (2) Counterfactual algorithms based uniquely on proximity loss functions are not actionable and will not provide meaningful explanations; (3) One cannot have meaningful evaluation results without guaranteeing plausibility in the counterfactual generation process. Algorithms that do not consider plausibility in their internal mechanisms will lead to biased and unreliable conclusions if evaluated with the current state-of-the-art metrics; (4) A qualitative analysis is strongly recommended (together with a quantitative analysis) to ensure a robust analysis of counterfactual explanations and the potential identification of biases.

The evolution of digital technology and the increasing popularity of sports inspired the innovators to take the experience of users with a proclivity towards sports to a whole new different level, by introducing Fantasy Sports Platforms FSPs. The application of Data Science and Analytics is Ubiquitous in the Modern World. Data Science and Analytics open doors to gain a deeper understanding and help in the decision making process. We firmly believed that we could adopt Data Science to predict the winning fantasy cricket team on the FSP, Dream 11. We built a predictive model that predicts the performance of players in a prospective game. We used a combination of Greedy and Knapsack Algorithms to prescribe the combination of 11 players to create a fantasy cricket team that has the most significant statistical odds of finishing as the strongest team thereby giving us a higher chance of winning the pot of bets on the Dream 11 FSP. We used PyCaret Python Library to help us understand and adopt the best Regressor Algorithm for our problem statement to make precise predictions. Further, we used Plotly Python Library to give us visual insights into the team, and players performances by accounting for the statistical, and subjective factors of a prospective game. The interactive plots help us to bolster the recommendations of our predictive model. You either win big, win small, or lose your bet based on the performance of the players selected for your fantasy team in the prospective game, and our model increases the probability of you winning big.

Data Science and Analytics have Basketball, Soccer, Tennis, and Cricket. In the modern world, optimized almost every domain that exists in the market. In Sports Analytics is found to be used in almost every our survey we tend to focus mainly how the field of organized sport that is played. Today, we have Sports Analytics has been adopted in the field of sports, how it has Analytics put into use in all primary sports right from Team-contributed to the transformation of the game right from the Selection and On-ground Decision making to business assessment of on-field players and their selection to aspects of the sport. The development of this domain had its prediction of winning team and to the marketing of tickets roots primarily from Statistics, Game Theory, and Decision and business aspects of big sports tournaments. We will Theory, and today, the field also uses Machine Learning and present the analytical tools, algorithms and methodologies Modern Analytical Approaches to decisions on the team and adopted in the field of Sports Analytics for different sports the game itself.

The advancements in machine learning techniques have encouraged researchers to apply these techniques to a myriad of software engineering tasks that use source code analysis, such as testing and vulnerability detection. Such a large number of studies hinders the community from understanding the current research landscape. This paper aims to summarize the current knowledge in applied machine learning for source code analysis. We review studies belonging to twelve categories of software engineering tasks and corresponding machine learning techniques, tools, and datasets that have been applied to solve them. To do so, we conducted an extensive literature search and identified 479 primary studies published between 2011 and 2021. We summarize our observations and findings with the help of the identified studies. Our findings suggest that the use of machine learning techniques for source code analysis tasks is consistently increasing. We synthesize commonly used steps and the overall workflow for each task and summarize machine learning techniques employed. We identify a comprehensive list of available datasets and tools useable in this context. Finally, the paper discusses perceived challenges in this area, including the availability of standard datasets, reproducibility and replicability, and hardware resources.