Have you been in a situation where you expected your machine learning model to perform really well but it sputtered out a poor accuracy? You've done all the hard work – so where did the classification model go wrong? How can you correct this? There are plenty of ways to gauge the performance of your classification model but none have stood the test of time like the confusion matrix. It helps us evaluate how our model performed, where it went wrong and offers us guidance to correct our path.

If you have ever tried to watch a live nest camera hoping to observe a falcon or other interesting bird, you may have had the experience of opening the live stream and seeing an empty nest. Not sure how long you should wait for the bird to return? In this article, I will describe my final project for the 12-week Metis Data Science Bootcamp that I attended January–March 2021. My project was aimed at automating nest monitoring for the Nottingham Trent University Falcon Cam. Using deep learning and automation tools, I designed a method for 24-hour bird detection that serves as an infrastructure upon which a Twitter bot or other notification system can be built to notify users when the bird enters or leaves the nest.

Banks, telephone service companies, Internet service providers, pay TV companies, insurance firms, and alarm monitoring services, often use customer attrition analysis and customer attrition rates as one of their key business metrics (along with cash flow, EBITDA, etc.) because the cost of retaining an existing customer is far less than acquiring a new one (Wikipedia). According to this article, the probability of selling to a new customer is 60-70%, while the probability of selling to a new prospect is 5-20%. So knowing if a customer is at risk of leaving is one of the most important tasks a company has to perform in order to keep growing its business. The data can be found here on kaggle public datasets. We will predict if a customer will churn based on his informations. There are 7043 customers and 20 features.

Predicting gender by the name is not a simple task. In many applications, especially in the natural language processing (NLP) field, this task may be necessary, mainly when considering foreign names. Some machine learning algorithms can satisfactorily perform the prediction. In this paper, we examined and implemented feedforward and recurrent deep neural network models, such as MLP, RNN, GRU, CNN, and BiLSTM, to classify gender through the first name. A dataset of Brazilian names is used to train and evaluate the models. We analyzed the accuracy, recall, precision, and confusion matrix to measure the models' performances. The results indicate that the gender prediction can be performed from the feature extraction strategy looking at the names as a set of strings. Some models accurately predict the gender in more than 90% of the cases. The recurrent models overcome the feedforward models in this binary classification problem.

QuaPy is an open-source framework for performing quantification (a.k.a. supervised prevalence estimation), written in Python. Quantification is the task of training quantifiers via supervised learning, where a quantifier is a predictor that estimates the relative frequencies (a.k.a. prevalence values) of the classes of interest in a sample of unlabelled data. While quantification can be trivially performed by applying a standard classifier to each unlabelled data item and counting how many data items have been assigned to each class, it has been shown that this "classify and count" method is outperformed by methods specifically designed for quantification. QuaPy provides implementations of a number of baseline methods and advanced quantification methods, of routines for quantification-oriented model selection, of several broadly accepted evaluation measures, and of robust evaluation protocols routinely used in the field. QuaPy also makes available datasets commonly used for testing quantifiers, and offers visualization tools for facilitating the analysis and interpretation of the results. The software is open-source and publicly available under a BSD-3 licence via https://github.com/HLT-ISTI/QuaPy, and can be installed via pip (https://pypi.org/project/QuaPy/)

Data fusion is a well-known technique, becoming more and more popular in the Artificial Intelligence for Earth Observation (AI4EO) domain mainly due to its ability of reinforcing AI4EO applications by combining multiple data sources and thus bringing better results. On the other hand, like other methods for satellite data analysis, data fusion itself is also benefiting and evolving thanks to the integration of Artificial Intelligence (AI). In this letter, four data fusion paradigms, based on Convolutional Neural Networks (CNNs), are analyzed and implemented. The goals are to provide a systematic procedure for choosing the best data fusion framework, resulting in the best classification results, once the basic structure for the CNN has been defined, and to help interested researchers in their work when data fusion applied to remote sensing is involved. The procedure has been validated for land-cover classification but it can be transferred to other cases.

Food security is more prominent on the policy agenda today than it has been in the past, thanks to recent food shortages at both the regional and global levels as well as renewed promises from major donor countries to combat chronic hunger. One field where machine learning can be used is in the classification of household food insecurity. In this study, we establish a robust methodology to categorize whether or not a household is being food secure and food insecure by machine learning algorithms. In this study, we have used ten machine learning algorithms to classify the food security status of the Household. Gradient Boosting (GB), Random Forest (RF), Extra Tree (ET), Bagging, K-Nearest Neighbor (KNN), Decision Tree (DT), Support Vector Machine (SVM), Logistic Regression (LR), Ada Boost (AB) and Naive Bayes were the classification algorithms used throughout this study (NB). Then, we perform classification tasks from developing data set for household food security status by gathering data from HICE survey data and validating it by Domain Experts. The performance of all classifiers has better results for all performance metrics. The performance of the Random Forest and Gradient Boosting models are outstanding with a testing accuracy of 0.9997 and the other classifier such as Bagging, Decision tree, Ada Boost, Extra tree, K-nearest neighbor, Logistic Regression, SVM and Naive Bayes are scored 0.9996, 0.09996, 0.9994, 0.95675, 0.9415, 0.8915, 0.7853 and 0.7595, respectively.

Causal discovery from observational data is an important but challenging task in many scientific fields. Recently, NOTEARS [Zheng et al., 2018] formulates the causal structure learning problem as a continuous optimization problem using least-square loss with an acyclicity constraint. Though the least-square loss function is well justified under the standard Gaussian noise assumption, it is limited if the assumption does not hold. In this work, we theoretically show that the violation of the Gaussian noise assumption will hinder the causal direction identification, making the causal orientation fully determined by the causal strength as well as the variances of noises in the linear case and the noises of strong non-Gaussianity in the nonlinear case. Consequently, we propose a more general entropy-based loss that is theoretically consistent with the likelihood score under any noise distribution. We run extensive empirical evaluations on both synthetic data and real-world data to validate the effectiveness of the proposed method and show that our method achieves the best in Structure Hamming Distance, False Discovery Rate, and True Positive Rate matrices.

Nowadays new technologies, and especially artificial intelligence, are more and more established in our society. Big data analysis and machine learning, two sub-fields of artificial intelligence, are at the core of many recent breakthroughs in many application fields (e.g., medicine, communication, finance, ...), including some that are strongly related to our day-to-day life (e.g., social networks, computers, smartphones, ...). In machine learning, significant improvements are usually achieved at the price of an increasing computational complexity and thanks to bigger datasets. Currently, cutting-edge models built by the most advanced machine learning algorithms typically became simultaneously very efficient and profitable but also extremely complex. Their complexity is to such an extent that these models are commonly seen as black-boxes providing a prediction or a decision which can not be interpreted or justified. Nevertheless, whether these models are used autonomously or as a simple decision-making support tool, they are already being used in machine learning applications where health and human life are at stake. Therefore, it appears to be an obvious necessity not to blindly believe everything coming out of those models without a detailed understanding of their predictions or decisions. Accordingly, this thesis aims at improving the interpretability of models built by a specific family of machine learning algorithms, the so-called tree-based methods. Several mechanisms have been proposed to interpret these models and we aim along this thesis to improve their understanding, study their properties, and define their limitations.

Kernel-based feature selection is an important tool in nonparametric statistics. Despite many practical applications of kernel-based feature selection, there is little statistical theory available to support the method. A core challenge is the objective function of the optimization problems used to define kernel-based feature selection are nonconvex. The literature has only studied the statistical properties of the \emph{global optima}, which is a mismatch, given that the gradient-based algorithms available for nonconvex optimization are only able to guarantee convergence to local minima. Studying the full landscape associated with kernel-based methods, we show that feature selection objectives using the Laplace kernel (and other $\ell_1$ kernels) come with statistical guarantees that other kernels, including the ubiquitous Gaussian kernel (or other $\ell_2$ kernels) do not possess. Based on a sharp characterization of the gradient of the objective function, we show that $\ell_1$ kernels eliminate unfavorable stationary points that appear when using an $\ell_2$ kernel. Armed with this insight, we establish statistical guarantees for $\ell_1$ kernel-based feature selection which do not require reaching the global minima. In particular, we establish model-selection consistency of $\ell_1$-kernel-based feature selection in recovering main effects and hierarchical interactions in the nonparametric setting with $n \sim \log p$ samples.