You might be one of the 730,000 people who have lost their jobs since the start of the coronavirus pandemic. Or maybe you're eyeing up your current industry and think it's time to get a shift on before things go sour. Business is booming in tech. Demand for digital services, from the likes of Zoom to Deliveroo, have demonstrated the impact tech has on the world around us and people want in. One of the biggest barriers to a tech career is often seen as a lack of coding knowledge.

Web scraping or crawling is the fact of fetching data from a third party website by downloading and parsing the HTML code to extract the data you want. But you should use an API for this! Not every website offers an API, and APIs don't always expose every piece of information you need. So it's often the only solution to extract website data. So, what is the problem? The main problem is that most websites do not want to be scraped.

Relevant research has been standing out in the computing community aiming to develop computational models capable of predicting occurrence of crimes, analyzing contexts of crimes, extracting profiles of individuals linked to crimes, and analyzing crimes according to time. This, due to the social impact and also the complex origin of the data, thus showing itself as an interesting computational challenge. This research presents a computational model for the prediction of homicide crimes, based on tabular data of crimes registered in the city of Bel\'em - Par\'a, Brazil. Statistical tests were performed with 8 different classification methods, both Random Forest, Logistic Regression, and Neural Network presented best results, AUC ~ 0.8. Results considered as a baseline for the proposed problem.

Probabilistic sentential decision diagrams are logic circuits where the inputs of disjunctive gates are annotated by probability values. They allow for a compact representation of joint probability mass functions defined over sets of Boolean variables, that are also consistent with the logical constraints defined by the circuit. The probabilities in such a model are usually learned from a set of observations. This leads to overconfident and prior-dependent inferences when data are scarce, unreliable or conflicting. In this work, we develop the credal sentential decision diagrams, a generalisation of their probabilistic counterpart that allows for replacing the local probabilities with (so-called credal) sets of mass functions. These models induce a joint credal set over the set of Boolean variables, that sharply assigns probability zero to states inconsistent with the logical constraints. Three inference algorithms are derived for these models, these allow to compute: (i) the lower and upper probabilities of an observation for an arbitrary number of variables; (ii) the lower and upper conditional probabilities for the state of a single variable given an observation; (iii) whether or not all the probabilistic sentential decision diagrams compatible with the credal specification have the same most probable explanation of a given set of variables given an observation of the other variables. These inferences are tractable, as all the three algorithms, based on bottom-up traversal with local linear programming tasks on the disjunctive gates, can be solved in polynomial time with respect to the circuit size. For a first empirical validation, we consider a simple application based on noisy seven-segment display images. The credal models are observed to properly distinguish between easy and hard-to-detect instances and outperform other generative models not able to cope with logical constraints.

Classification is a well-studied machine learning task which concerns the assignment of instances to a set of outcomes. Classification models support the optimization of managerial decision-making across a variety of operational business processes. For instance, customer churn prediction models are adopted to increase the efficiency of retention campaigns by optimizing the selection of customers that are to be targeted. Cost-sensitive and causal classification methods have independently been proposed to improve the performance of classification models. The former considers the benefits and costs of correct and incorrect classifications, such as the benefit of a retained customer, whereas the latter estimates the causal effect of an action, such as a retention campaign, on the outcome of interest. This study integrates cost-sensitive and causal classification by elaborating a unifying evaluation framework. The framework encompasses a range of existing and novel performance measures for evaluating both causal and conventional classification models in a cost-sensitive as well as a cost-insensitive manner. We proof that conventional classification is a specific case of causal classification in terms of a range of performance measures when the number of actions is equal to one. The framework is shown to instantiate to application-specific cost-sensitive performance measures that have been recently proposed for evaluating customer retention and response uplift models, and allows to maximize profitability when adopting a causal classification model for optimizing decision-making. The proposed framework paves the way toward the development of cost-sensitive causal learning methods and opens a range of opportunities for improving data-driven business decision-making.

We introduce Auto-Surprise, an Automated Recommender System library. Auto-Surprise is an extension of the Surprise recommender system library and eases the algorithm selection and configuration process. Compared to out-of-the-box Surprise library, Auto-Surprise performs better when evaluated with MovieLens, Book Crossing and Jester Datasets. It may also result in the selection of an algorithm with significantly lower runtime. Compared to Surprise's grid search, Auto-Surprise performs equally well or slightly better in terms of RMSE, and is notably faster in finding the optimum hyperparameters.

Recent progress in deep learning has led to the development of Optical Character Recognition (OCR) systems which perform remarkably well. Most research has been around recurrent networks as well as complex gated layers which make the overall solution complex and difficult to scale. In this paper, we present an Efficient And Scalable TExt Recognizer (EASTER) to perform optical character recognition on both machine printed and handwritten text. Our model utilises 1-D convolutional layers without any recurrence which enables parallel training with considerably less volume of data. We experimented with multiple variations of our architecture and one of the smallest variant (depth and number of parameter wise) performs comparably to RNN based complex choices. Our 20-layered deepest variant outperforms RNN architectures with a good margin on benchmarking datasets like IIIT-5k and SVT. We also showcase improvements over the current best results on offline handwritten text recognition task. We also present data generation pipelines with augmentation setup to generate synthetic datasets for both handwritten and machine printed text.

Machine Learning (ML) algorithms have been successfully employed by a vast range of practitioners with different backgrounds. One of the reasons for ML popularity is the capability to consistently delivers accurate results, which can be further boosted by adjusting hyperparameters (HP). However, part of practitioners has limited knowledge about the algorithms and does not take advantage of suitable HP settings. In general, HP values are defined by trial and error, tuning, or by using default values. Trial and error is very subjective, time costly and dependent on the user experience. Tuning techniques search for HP values able to maximize the predictive performance of induced models for a given dataset, but with the drawback of a high computational cost and target specificity. To avoid tuning costs, practitioners use default values suggested by the algorithm developer or by tools implementing the algorithm. Although default values usually result in models with acceptable predictive performance, different implementations of the same algorithm can suggest distinct default values. To maintain a balance between tuning and using default values, we propose a strategy to generate new optimized default values. Our approach is grounded on a small set of optimized values able to obtain predictive performance values better than default settings provided by popular tools. The HP candidates are estimated through a pool of promising values tuned from a small and informative set of datasets. After performing a large experiment and a careful analysis of the results, we concluded that our approach delivers better default values. Besides, it leads to competitive solutions when compared with the use of tuned values, being easier to use and having a lower cost.Based on our results, we also extracted simple rules to guide practitioners in deciding whether using our new methodology or a tuning approach.

Despite the availability of benchmark machine learning (ML) repositories (e.g., UCI, OpenML), there is no standard evaluation strategy yet capable of pointing out which is the best set of datasets to serve as gold standard to test different ML algorithms. In recent studies, Item Response Theory (IRT) has emerged as a new approach to elucidate what should be a good ML benchmark. This work applied IRT to explore the well-known OpenML-CC18 benchmark to identify how suitable it is on the evaluation of classifiers. Several classifiers ranging from classical to ensembles ones were evaluated using IRT models, which could simultaneously estimate dataset difficulty and classifiers' ability. The Glicko-2 rating system was applied on the top of IRT to summarize the innate ability and aptitude of classifiers. It was observed that not all datasets from OpenML-CC18 are really useful to evaluate classifiers. Most datasets evaluated in this work (84%) contain easy instances in general (e.g., around 10% of difficult instances only). Also, 80% of the instances in half of this benchmark are very discriminating ones, which can be of great use for pairwise algorithm comparison, but not useful to push classifiers abilities. This paper presents this new evaluation methodology based on IRT as well as the tool decodIRT, developed to guide IRT estimation over ML benchmarks.

Rarely has a crisis accelerated the adoption of a technology in the manner that is occurring today with AI in the food industry. The business of selling food to consumers is being disrupted to a degree not since the last pandemic, over 100 years ago. It is increasingly apparent that our food system was ill prepared ('anti-fragile') for this Covid-19 induced crisis. With restaurants shuttered, a dramatic return to home cooking, a re-ignition in the meal-kit movement, shut-downs of meat factories and office canteens, and explosion of home delivery it may seem as though the world will never be the same again. This too, of course, will pass, but instead of being a 6 month blip, the continued deconstruction and automation of the food supply process makes it clear that we are entering a new norm, and that returning to the world as we knew it won't be possible.