Albert Queraltó — Machine Learning and Data Engineering

Albert Queraltó — Machine Learning and Data EngineeringArticles about machine learning, data systems, model validation, and production engineering.https://albertqueralto.dev/Building an Invoice Late-Payment Predictor with Python and Scikit-learnhttps://albertqueralto.dev/blog/duesignal/https://albertqueralto.dev/blog/duesignal/How I designed DueSignal’s machine-learning pipeline to predict late invoice payments without data leakage, evaluate probability quality, and turn model outputs into actionable collection priorities.Sat, 25 Jul 2026 00:00:00 GMTMachine LearningScikit-learnPythonFintechMLOpsFeature Engineering for Machine Learning: Practical Techniqueshttps://albertqueralto.dev/blog/feature-engineering-ml/https://albertqueralto.dev/blog/feature-engineering-ml/The often-overlooked craft of transforming raw data into informative features — covering encoding, scaling, missing values, interactions, and selection.Wed, 20 May 2026 00:00:00 GMTFeature EngineeringMachine LearningScikit-learnData ScienceDiffusion Models Explained: The Math Behind Stable Diffusionhttps://albertqueralto.dev/blog/diffusion-models/https://albertqueralto.dev/blog/diffusion-models/How denoising diffusion probabilistic models learn to generate images by reversing a gradual noising process — explained from the ground up.Wed, 06 May 2026 00:00:00 GMTGenerative AIDiffusion ModelsDeep LearningComputer VisionTime Series Anomaly Detection with LSTMshttps://albertqueralto.dev/blog/lstm-anomaly-detection/https://albertqueralto.dev/blog/lstm-anomaly-detection/How to build a robust anomaly detection pipeline for multivariate sensor data using LSTM autoencoders in PyTorch, with practical tips on thresholding and deployment.Wed, 22 Apr 2026 00:00:00 GMTTime SeriesLSTMAnomaly DetectionPyTorchMLOpsConvolutional Neural Networks: How Machines Seehttps://albertqueralto.dev/blog/convolutional-neural-networks/https://albertqueralto.dev/blog/convolutional-neural-networks/A ground-up explanation of CNNs — convolution, pooling, receptive fields, and the architectural choices that made deep learning work for images.Wed, 08 Apr 2026 00:00:00 GMTComputer VisionCNNDeep LearningPyTorchGradient Descent Optimizers: From SGD to Adamhttps://albertqueralto.dev/blog/gradient-descent-optimizers/https://albertqueralto.dev/blog/gradient-descent-optimizers/A practical guide to the most widely used optimization algorithms in deep learning — what they compute, why they differ, and when to use each one.Wed, 25 Mar 2026 00:00:00 GMTDeep LearningOptimizationPyTorchTrainingUnderstanding Transformers: The Architecture Behind Modern NLPhttps://albertqueralto.dev/blog/understanding-transformers/https://albertqueralto.dev/blog/understanding-transformers/A deep dive into the self-attention mechanism and how transformers replaced recurrent networks to become the foundation of modern language models.Tue, 10 Mar 2026 00:00:00 GMTNLPDeep LearningTransformersPyTorch