An independent publication about data science and AI: the ideas explained from first principles, plus data cleaning, evaluation, SQL, experiments, and the judgment calls the tutorials skip.https://dataacademy.ai/https://dataacademy.ai/blog/incremental-tables-without-drift/https://dataacademy.ai/blog/incremental-tables-without-drift/Full rebuilds stop being affordable, incremental builds start being wrong. How to pick the incremental key, handle late data, and catch drift before a stakeholder does.Thu, 13 Aug 2026 23:00:00 GMTSQLProductionhttps://dataacademy.ai/blog/model-monitoring-and-drift/https://dataacademy.ai/blog/model-monitoring-and-drift/Data drift, concept drift, and delayed labels: a minimal monitoring setup that catches decay before the business does, without buying a platform.Wed, 12 Aug 2026 23:00:00 GMTProductionEvaluationhttps://dataacademy.ai/blog/when-you-cannot-randomise-users/https://dataacademy.ai/blog/when-you-cannot-randomise-users/Interference, marketplaces and features that leak between groups. Cluster and geo randomisation, switchback tests, and the observational fallbacks with their assumptions stated.Tue, 11 Aug 2026 23:00:00 GMTExperimentationCausal Inferencehttps://dataacademy.ai/blog/cohort-retention-in-sql/https://dataacademy.ai/blog/cohort-retention-in-sql/How to build a retention table that survives contact with real data: cohort definition, a period spine, and the bug that makes retention look like it is improving.Sun, 09 Aug 2026 23:00:00 GMTSQLCommunicationhttps://dataacademy.ai/blog/regression-metrics-mae-rmse-mape/https://dataacademy.ai/blog/regression-metrics-mae-rmse-mape/Each error metric implies a different "best" prediction — median, mean, or something biased low. Choose by the cost of being wrong, not by habit.Sun, 09 Aug 2026 23:00:00 GMTEvaluationStatisticshttps://dataacademy.ai/blog/sizing-an-experiment-before-you-run-it/https://dataacademy.ai/blog/sizing-an-experiment-before-you-run-it/Power analysis without the ritual: choosing the smallest effect worth detecting, what drives the sample size, and why an underpowered test is worse than no test.Thu, 06 Aug 2026 23:00:00 GMTExperimentationStatisticshttps://dataacademy.ai/blog/outliers-and-robust-statistics/https://dataacademy.ai/blog/outliers-and-robust-statistics/An outlier is an error, a whale, or a discovery — three different treatments. Robust statistics, sensible detection, and the customers you should not trim away.Wed, 05 Aug 2026 23:00:00 GMTStatisticsData Cleaninghttps://dataacademy.ai/blog/mutual-information-for-feature-selection/https://dataacademy.ai/blog/mutual-information-for-feature-selection/It catches relationships correlation misses, including ones you do not want. What it measures, why estimating it is hard, and why a high score can mean a leak.Tue, 04 Aug 2026 23:00:00 GMTInformation TheoryFeature Engineeringhttps://dataacademy.ai/blog/from-notebook-to-production/https://dataacademy.ai/blog/from-notebook-to-production/Notebooks are where analysis is born, not where it should live. A low-drama path: extract functions, add tests for data logic, parameterise, and schedule a script.Sun, 02 Aug 2026 23:00:00 GMTProductionPythonhttps://dataacademy.ai/blog/dbscan-and-density-based-clustering/https://dataacademy.ai/blog/dbscan-and-density-based-clustering/k-means needs k and assumes round clusters of similar size. Density-based clustering needs neither, and it can say that a point belongs to nothing at all.Sat, 01 Aug 2026 23:00:00 GMTClusteringMachine Learninghttps://dataacademy.ai/blog/cross-entropy-log-loss-and-perplexity/https://dataacademy.ai/blog/cross-entropy-log-loss-and-perplexity/Three names from three fields for one quantity: how surprised your model was. Where each shows up, how to read the units, and what a good value looks like.Wed, 29 Jul 2026 23:00:00 GMTInformation TheoryEvaluationhttps://dataacademy.ai/blog/sql-or-pandas-where-to-compute/https://dataacademy.ai/blog/sql-or-pandas-where-to-compute/A practical rule for splitting work between the warehouse and your laptop: aggregate where the data lives, iterate where your tools live.Wed, 29 Jul 2026 23:00:00 GMTSQLPythonhttps://dataacademy.ai/blog/data-validation-with-schemas/https://dataacademy.ai/blog/data-validation-with-schemas/Upstream will change without telling you. Explicit schema and expectation checks at pipeline boundaries turn silent corruption into loud, early failures.Sun, 26 Jul 2026 23:00:00 GMTData CleaningProductionPythonhttps://dataacademy.ai/blog/partial-dependence-and-what-it-assumes/https://dataacademy.ai/blog/partial-dependence-and-what-it-assumes/PDPs average over the rest of the data, which means they can describe combinations that never occur. ICE curves, correlated features, and how to read both without overclaiming.Wed, 22 Jul 2026 23:00:00 GMTInterpretabilityMachine Learninghttps://dataacademy.ai/blog/reproducibility-checklist/https://dataacademy.ai/blog/reproducibility-checklist/Seeds, pinned environments, data snapshots, and one-command reruns — the practical minimum for results you can regenerate in six months.Wed, 22 Jul 2026 23:00:00 GMTProductionPythonhttps://dataacademy.ai/blog/are-your-clusters-real/https://dataacademy.ai/blog/are-your-clusters-real/k-means always returns clusters, including on noise. How to tell structure from partition: stability, internal indices, and the check most people skip.Wed, 15 Jul 2026 23:00:00 GMTClusteringEvaluationhttps://dataacademy.ai/blog/communicating-results-to-stakeholders/https://dataacademy.ai/blog/communicating-results-to-stakeholders/The decision is the deliverable. How to structure findings for people who will never read your notebook — answer first, uncertainty in plain language, units they own.Wed, 15 Jul 2026 23:00:00 GMTCommunicationhttps://dataacademy.ai/blog/feature-importance-is-not-explanation/https://dataacademy.ai/blog/feature-importance-is-not-explanation/Impurity importance, permutation importance, and SHAP each answer a narrower question than people think — and none of them answers "what causes what".Wed, 08 Jul 2026 23:00:00 GMTInterpretabilityMachine Learninghttps://dataacademy.ai/blog/seasonality-holidays-and-calendar-features/https://dataacademy.ai/blog/seasonality-holidays-and-calendar-features/Most time series move on a calendar, not a trend. Which calendar features actually help, why one-hot day-of-week is usually wrong, and the holidays that break every model.Wed, 08 Jul 2026 23:00:00 GMTTime SeriesFeature Engineeringhttps://dataacademy.ai/blog/class-imbalance-thresholds-not-smote/https://dataacademy.ai/blog/class-imbalance-thresholds-not-smote/Imbalanced classes are usually a thresholding and metrics problem, not a data problem. What actually helps, what mostly does not, how to pick a threshold from the cost of each mistake, and in which order to try things.Wed, 01 Jul 2026 23:00:00 GMTMachine LearningEvaluationhttps://dataacademy.ai/blog/tfidf-still-works/https://dataacademy.ai/blog/tfidf-still-works/Before reaching for a transformer: a TF-IDF plus linear classifier baseline trains in seconds, explains itself, and is embarrassingly hard to beat on many text tasks.Sun, 28 Jun 2026 23:00:00 GMTNLPMachine Learninghttps://dataacademy.ai/blog/always-build-a-dumb-baseline/https://dataacademy.ai/blog/always-build-a-dumb-baseline/Majority class, yesterday-equals-today, one rule of thumb: an hour spent on a deliberately dumb baseline is the best ROI in a data project.Wed, 24 Jun 2026 23:00:00 GMTEvaluationMachine LearningFoundationshttps://dataacademy.ai/blog/backtesting-a-forecast-honestly/https://dataacademy.ai/blog/backtesting-a-forecast-honestly/Rolling-origin evaluation, the baselines a forecast must beat, and the quiet ways a backtest ends up scoring information the model would never have had.Wed, 24 Jun 2026 23:00:00 GMTTime SeriesEvaluationhttps://dataacademy.ai/blog/calibration-when-probabilities-lie/https://dataacademy.ai/blog/calibration-when-probabilities-lie/Probability calibration: why good classifiers output bad probabilities, how to see it with a reliability curve, and when Platt scaling or isotonic regression fixes it.Wed, 17 Jun 2026 23:00:00 GMTEvaluationProbabilityMachine Learninghttps://dataacademy.ai/blog/reading-shap-values-correctly/https://dataacademy.ai/blog/reading-shap-values-correctly/SHAP explains one prediction against a baseline, not the world. What the numbers mean, what the plots hide, and the readings that get a model into trouble.Wed, 17 Jun 2026 23:00:00 GMTInterpretabilityMachine Learninghttps://dataacademy.ai/blog/pandas-cleaning-patterns/https://dataacademy.ai/blog/pandas-cleaning-patterns/Method chaining, assign, vectorized string ops, coercion audits, and validation asserts — a working style for cleaning code you can still read in six months.Wed, 10 Jun 2026 23:00:00 GMTData CleaningPythonhttps://dataacademy.ai/blog/bandits-are-the-rl-you-will-actually-use/https://dataacademy.ai/blog/bandits-are-the-rl-you-will-actually-use/Full RL rarely survives contact with a business problem. Multi-armed bandits do: the same explore-exploit trade, without the state, the simulator or the reward engineering.Wed, 03 Jun 2026 23:00:00 GMTReinforcement LearningExperimentationhttps://dataacademy.ai/blog/encoding-categorical-variables/https://dataacademy.ai/blog/encoding-categorical-variables/One-hot, ordinal, target encoding, and the high-cardinality problem — which encoding to use when, and the leakage trap inside target encoding.Wed, 03 Jun 2026 23:00:00 GMTFeature EngineeringMachine Learninghttps://dataacademy.ai/blog/gradient-boosting-default-for-tabular/https://dataacademy.ai/blog/gradient-boosting-default-for-tabular/Why LightGBM/XGBoost keep beating neural networks on tables, the five hyperparameters that matter, and the standard mistakes — including early stopping done wrong.Sun, 31 May 2026 23:00:00 GMTMachine LearningPythonhttps://dataacademy.ai/blog/missing-data-is-information/https://dataacademy.ai/blog/missing-data-is-information/Why dropna() is a modelling decision in disguise, the three mechanisms of missingness, and imputation patterns that do not bury the signal.Wed, 27 May 2026 23:00:00 GMTData CleaningFeature Engineeringhttps://dataacademy.ai/blog/time-series-forecasting-pitfalls/https://dataacademy.ai/blog/time-series-forecasting-pitfalls/Random splits, ignored baselines, leaking features, log-space metrics, and one-step myopia — the mistakes that make forecasts look better than they are.Wed, 20 May 2026 23:00:00 GMTTime SeriesEvaluationhttps://dataacademy.ai/blog/embeddings-a-practical-introduction/https://dataacademy.ai/blog/embeddings-a-practical-introduction/What embedding vectors actually are, what they are good for besides chatbots, and the operational details — normalisation, chunking, drift — that tutorials skip.Wed, 13 May 2026 23:00:00 GMTNLPDeep Learninghttps://dataacademy.ai/blog/ab-test-pitfalls-peeking-and-power/https://dataacademy.ai/blog/ab-test-pitfalls-peeking-and-power/Peeking, underpowered tests, and twenty metrics with one winner: the three failure modes that produce most false experiment wins, and the working defenses.Wed, 06 May 2026 23:00:00 GMTExperimentationStatisticshttps://dataacademy.ai/blog/bootstrap-confidence-intervals/https://dataacademy.ai/blog/bootstrap-confidence-intervals/Resample your data with replacement, recompute the statistic, read the spread — honest confidence intervals for medians, ratios, AUCs, and anything else.Sun, 03 May 2026 23:00:00 GMTStatisticsPythonhttps://dataacademy.ai/blog/cross-validation-without-fooling-yourself/https://dataacademy.ai/blog/cross-validation-without-fooling-yourself/K-fold is the easy part. Grouped data, temporal data, and the quiet ways a validation scheme overstates how good your model really is.Wed, 29 Apr 2026 23:00:00 GMTEvaluationMachine Learninghttps://dataacademy.ai/blog/accuracy-is-the-wrong-metric/https://dataacademy.ai/blog/accuracy-is-the-wrong-metric/On imbalanced problems, a model that does nothing scores 99%. Precision, recall, PR curves, and how to pick a metric that matches the cost of being wrong.Wed, 22 Apr 2026 23:00:00 GMTEvaluationMachine Learninghttps://dataacademy.ai/blog/data-leakage-is-why-your-model-looks-great/https://dataacademy.ai/blog/data-leakage-is-why-your-model-looks-great/If your validation score seems miraculous, the most likely explanation is that the answer leaked into the features. The common leaks, two worked through end to end, and how to audit for them.Wed, 15 Apr 2026 23:00:00 GMTEvaluationData CleaningMachine Learninghttps://dataacademy.ai/blog/sql-window-functions-you-actually-need/https://dataacademy.ai/blog/sql-window-functions-you-actually-need/ROW_NUMBER, LAG, SUM OVER, and moving averages — with the patterns for deduplication, sessionisation, and running totals you will reuse for years, plus FILTER, QUALIFY, ROWS versus RANGE, and what a window actually costs.Wed, 08 Apr 2026 23:00:00 GMTSQLhttps://dataacademy.ai/blog/simpsons-paradox-in-dashboards/https://dataacademy.ai/blog/simpsons-paradox-in-dashboards/Aggregates can reverse when you split by segment — a mix-shift illusion that routinely misleads metric reviews. How to spot it and which number to trust.Sun, 05 Apr 2026 23:00:00 GMTStatisticsCausal InferenceCommunicationhttps://dataacademy.ai/blog/feature-engineering-that-survives-production/https://dataacademy.ai/blog/feature-engineering-that-survives-production/A feature that boosts your offline metrics but cannot be computed at prediction time is worse than useless. How to build features that keep working after deployment.Wed, 01 Apr 2026 23:00:00 GMTFeature EngineeringProductionhttps://dataacademy.ai/blog/when-it-is-not-a-data-problem/https://dataacademy.ai/blog/when-it-is-not-a-data-problem/Some requests do not need a model, a dashboard, or you. Recognising them early is the highest-leverage thing a data person does, and the least rewarded.Wed, 01 Apr 2026 23:00:00 GMTFramingCommunicationhttps://dataacademy.ai/blog/start-with-the-simplest-model/https://dataacademy.ai/blog/start-with-the-simplest-model/Linear regression is not beneath you. Reaching for deep learning first is usually a mistake — here is the discipline that replaces it, and when to escalate.Fri, 27 Mar 2026 00:00:00 GMTMachine LearningFoundationshttps://dataacademy.ai/blog/choosing-the-unit-of-analysis/https://dataacademy.ai/blog/choosing-the-unit-of-analysis/Per user, per session, per order, per day. The choice quietly decides what your numbers mean, and getting it wrong invalidates the analysis before it starts.Thu, 19 Mar 2026 00:00:00 GMTFramingStatisticshttps://dataacademy.ai/blog/sampling-logs-properly/https://dataacademy.ai/blog/sampling-logs-properly/head(1000) is not a sample. Random, stratified, and entity-level sampling in SQL and pandas — and the bias traps in each.Thu, 19 Mar 2026 00:00:00 GMTStatisticsData Cleaninghttps://dataacademy.ai/blog/the-job-is-mostly-cleaning/https://dataacademy.ai/blog/the-job-is-mostly-cleaning/Courses spend 5% of the time on the 80% of the work. What data cleaning actually involves, why it is the real skill, and how to get good at it deliberately.Thu, 12 Mar 2026 00:00:00 GMTData CleaningFoundationshttps://dataacademy.ai/blog/from-request-to-question/https://dataacademy.ai/blog/from-request-to-question/Stakeholders ask for dashboards and models. Underneath is a decision someone needs to make. How to find it before you build the wrong thing.Thu, 05 Mar 2026 00:00:00 GMTFramingCommunicationhttps://dataacademy.ai/blog/markov-chains-explained/https://dataacademy.ai/blog/markov-chains-explained/What a Markov chain is, why the memoryless assumption is less crazy than it sounds, how a chain settles into a long-run distribution, and where you meet one in real work.Thu, 31 Jul 2025 23:00:00 GMTFoundationsProbabilityhttps://dataacademy.ai/blog/how-a-model-gets-trained-pretraining-to-rlhf/https://dataacademy.ai/blog/how-a-model-gets-trained-pretraining-to-rlhf/The three stages that turn raw text into a chat assistant, what each one actually changes about the model, and why the base model and the assistant are different things.Wed, 12 Feb 2025 00:00:00 GMTFoundationsLLMsReinforcement Learninghttps://dataacademy.ai/blog/what-a-language-model-is-doing/https://dataacademy.ai/blog/what-a-language-model-is-doing/A first-principles look at large language models: next-token prediction, why that simple goal produces apparent reasoning, and what temperature and sampling really control.Wed, 27 Nov 2024 00:00:00 GMTFoundationsLLMshttps://dataacademy.ai/blog/attention-is-the-whole-trick/https://dataacademy.ai/blog/attention-is-the-whole-trick/Queries, keys and values in plain language: how a word picks up meaning from its neighbours, and why one matrix multiplication solved the long-range dependency problem.Sat, 13 Apr 2024 23:00:00 GMTFoundationsLLMsDeep Learninghttps://dataacademy.ai/blog/transformers-explained-from-scratch/https://dataacademy.ai/blog/transformers-explained-from-scratch/Tokens, embeddings and a stack of identical blocks — how a transformer turns next-word prediction into a training objective, and why it trains in parallel where RNNs could not.Sun, 07 Apr 2024 23:00:00 GMTFoundationsLLMsDeep Learninghttps://dataacademy.ai/blog/why-prompting-works/https://dataacademy.ai/blog/why-prompting-works/Prompting is conditioning, not magic words. Understanding what the prompt does to the probability distribution explains which techniques help and which are folklore.Mon, 07 Aug 2023 23:00:00 GMTFoundationsLLMshttps://dataacademy.ai/blog/entropy-and-information-explained/https://dataacademy.ai/blog/entropy-and-information-explained/Information as surprise, why bits fall out of a logarithm, and the straight line from there to the cross-entropy loss you train with and the splits a decision tree picks.Fri, 07 Jul 2023 23:00:00 GMTFoundationsInformation TheoryProbabilityhttps://dataacademy.ai/blog/why-language-models-hallucinate/https://dataacademy.ai/blog/why-language-models-hallucinate/Hallucination is not a bug in the usual sense. It follows from what the model is trained to do, and only some of the popular fixes address the actual cause.Wed, 26 Apr 2023 23:00:00 GMTFoundationsLLMsEvaluationhttps://dataacademy.ai/blog/the-central-limit-theorem-explained/https://dataacademy.ai/blog/the-central-limit-theorem-explained/Why sums of many small independent effects turn into a bell curve, what the theorem promises about sample means, where it fails, and why "n > 30" is folklore.Tue, 21 Mar 2023 00:00:00 GMTFoundationsStatisticsProbabilityhttps://dataacademy.ai/blog/convolution-how-computers-see/https://dataacademy.ai/blog/convolution-how-computers-see/What a convolution actually does to an image, why sliding a tiny grid of numbers finds edges, and why learning those numbers instead of designing them changed computer vision.Fri, 25 Nov 2022 00:00:00 GMTFoundationsComputer VisionDeep Learninghttps://dataacademy.ai/blog/how-diffusion-models-make-images/https://dataacademy.ai/blog/how-diffusion-models-make-images/The idea behind AI image generators, explained plainly: teach a model to remove noise from a picture, and running it in reverse from pure static gives you a picture.Tue, 07 Jun 2022 23:00:00 GMTFoundationsComputer VisionDeep Learninghttps://dataacademy.ai/blog/monte-carlo-methods-explained/https://dataacademy.ai/blog/monte-carlo-methods-explained/When the maths is too hard, sample instead. What Monte Carlo is from first principles, why error falls as one over root n, and where it earns its keep in real work.Mon, 14 Sep 2020 23:00:00 GMTFoundationsProbabilityPythonhttps://dataacademy.ai/blog/reinforcement-learning-what-alphago-taught/https://dataacademy.ai/blog/reinforcement-learning-what-alphago-taught/Learning from consequences instead of answers: agent, reward, and the credit assignment problem — plus an honest account of why reinforcement learning is rare in normal data work.Fri, 20 Mar 2020 00:00:00 GMTFoundationsReinforcement LearningMachine Learninghttps://dataacademy.ai/blog/bayes-theorem-from-first-principles/https://dataacademy.ai/blog/bayes-theorem-from-first-principles/Bayes as areas and counts rather than a formula: the medical-test example worked properly, why base rates dominate, and where the idea earns its keep in practice.Sun, 29 Dec 2019 00:00:00 GMTFoundationsProbabilityStatisticshttps://dataacademy.ai/blog/what-word-embeddings-really-are/https://dataacademy.ai/blog/what-word-embeddings-really-are/Why representing words as IDs fails, how counting the company a word keeps turns language into geometry, and what the famous king-minus-man analogy does and does not prove.Wed, 30 Oct 2019 00:00:00 GMTFoundationsNLPDeep Learninghttps://dataacademy.ai/blog/gradient-boosting-from-first-principles/https://dataacademy.ai/blog/gradient-boosting-from-first-principles/How boosting works from scratch: fit a model, fit the next one to what the first got wrong, then repeat. Why that is not bagging, and what the learning rate really buys.Sun, 31 Mar 2019 23:00:00 GMTFoundationsMachine Learninghttps://dataacademy.ai/blog/overfitting-and-the-bias-variance-tradeoff/https://dataacademy.ai/blog/overfitting-and-the-bias-variance-tradeoff/What overfitting really is, what bias and variance each mean in concrete terms, how the tradeoff shows up in model choice, and where the classic curve stops holding.Sun, 23 Sep 2018 23:00:00 GMTFoundationsMachine LearningEvaluationhttps://dataacademy.ai/blog/k-means-clustering-explained/https://dataacademy.ai/blog/k-means-clustering-explained/The assign-and-update loop from scratch, what k-means actually minimises, why it only finds round clusters of similar size, and how to choose k without fooling yourself.Tue, 29 May 2018 23:00:00 GMTFoundationsClusteringMachine Learninghttps://dataacademy.ai/blog/gans-and-why-deepfakes-work/https://dataacademy.ai/blog/gans-and-why-deepfakes-work/How training two networks against each other produces convincing fake images, why that setup is famously unstable, and what it sensibly changes about trusting a video.Fri, 04 May 2018 23:00:00 GMTFoundationsDeep LearningComputer Visionhttps://dataacademy.ai/blog/pca-explained-from-first-principles/https://dataacademy.ai/blog/pca-explained-from-first-principles/What a principal component actually is, why scaling comes first, how to read a scree plot, and the two things people wrongly expect PCA to do for them.Sun, 08 Apr 2018 23:00:00 GMTFoundationsMachine LearningStatisticshttps://dataacademy.ai/blog/logistic-regression-from-first-principles/https://dataacademy.ai/blog/logistic-regression-from-first-principles/Why a straight line cannot predict probabilities, what the log-odds link fixes, how to read a coefficient as an odds ratio, and why the loss is cross-entropy.Mon, 12 Mar 2018 00:00:00 GMTFoundationsMachine Learninghttps://dataacademy.ai/blog/decision-trees-and-random-forests/https://dataacademy.ai/blog/decision-trees-and-random-forests/How a tree decides which question to ask, why a single deep tree memorises its training data, and why averaging hundreds of decorrelated trees fixes it.Mon, 12 Feb 2018 00:00:00 GMTFoundationsMachine Learninghttps://dataacademy.ai/blog/backpropagation-explained-plainly/https://dataacademy.ai/blog/backpropagation-explained-plainly/How a network works out which weight was to blame for a wrong answer, why the chain rule is really credit assignment, and why backprop is bookkeeping rather than magic.Fri, 10 Nov 2017 00:00:00 GMTFoundationsNeural NetworksDeep Learninghttps://dataacademy.ai/blog/simpsons-paradox-from-first-principles/https://dataacademy.ai/blog/simpsons-paradox-from-first-principles/Why an average over groups can point the opposite way to every group inside it, what the Berkeley admissions case actually showed, and how to decide which number to act on.Tue, 31 Oct 2017 00:00:00 GMTFoundationsStatisticsCausal Inferencehttps://dataacademy.ai/blog/gradient-descent-from-first-principles/https://dataacademy.ai/blog/gradient-descent-from-first-principles/The cost surface, why the gradient points uphill, what the learning rate really controls, and why local minima matter far less in practice than everyone expects.Sun, 22 Oct 2017 23:00:00 GMTFoundationsNeural NetworksDeep Learninghttps://dataacademy.ai/blog/what-a-neural-network-actually-is/https://dataacademy.ai/blog/what-a-neural-network-actually-is/Layers, weights, biases and activations built up from scratch on the handwritten-digit problem, and why "learning" means nothing more exotic than adjusting a pile of numbers.Wed, 11 Oct 2017 23:00:00 GMTFoundationsNeural NetworksDeep Learninghttps://dataacademy.ai/blog/p-values-what-they-do-and-dont-say/https://dataacademy.ai/blog/p-values-what-they-do-and-dont-say/What a p-value actually measures, the four things it gets mistaken for, how forking paths produce small p-values from nothing, and what to report instead.Wed, 17 Aug 2016 23:00:00 GMTFoundationsStatisticsExperimentationhttps://dataacademy.ai/blog/automation-and-jobs-a-data-view/https://dataacademy.ai/blog/automation-and-jobs-a-data-view/Why "will automation take my job" is the wrong question, what a task-level view shows that a job-level view hides, and how to reason about it without hype or doom.Tue, 19 Aug 2014 23:00:00 GMTFoundationsMachine LearningCommunicationhttps://dataacademy.ai/blog/correlation-is-not-causation-but/https://dataacademy.ai/blog/correlation-is-not-causation-but/The three things that can produce any correlation, why the famous slogan stops thought instead of starting it, and what actually establishes a causal claim.Wed, 24 Aug 2011 23:00:00 GMTFoundationsCausal InferenceStatisticshttps://dataacademy.ai/blog/the-monty-hall-problem/https://dataacademy.ai/blog/the-monty-hall-problem/Three doors, one car, a host who knows where it is. Switching wins two thirds of the time — here is the intuition, the enumeration, and the lesson underneath it.Sun, 28 Jan 2007 00:00:00 GMTFoundationsProbability