Meta tags:
description=Your home for data science and AI. The world’s leading publication for data science, data analytics, data engineering, machine learning, and artificial intelligence professionals.;

Headings (most frequently used words):

the, in, learning, and, for, advent, machine, to, ai, what, calendar, excel, how, with, of, agents, optimize, deep, llms, code, about, data, an, variable, rag, bonus, gradient, control, auc, programming, vs, your, python, understanding, pipeline, linear, newsletter, day, eda, public, part, rfm, analysis, customer, segmentation, pandas, reinforcement, actor, critic, method, latest, production, ready, made, simple, nemo, agent, toolkit, has, taught, me, science, chunk, size, as, experimental, systems, descent, variants, overcoming, nonsmoothness, chattering, nonconvex, optimal, problems, under, curve, facilitate, effective, engineer, are, differences, editor, picks, exploring, tabpfn, foundation, model, built, tabular, think, is, slow, stop, guessing, start, measuring, keeping, probabilities, honest, jacobian, adjustment, why, map, mrr, fail, search, ranking, use, instead, bonferroni, benjamini, hochberg, choosing, value, correction, vibe, proving, running, evals, on, bloated, generative, user, optimized, my, leaf, raking, strategy, using, 2025, must, reads, more, tds, or, art, making, everything, better, dives, build, powered, weather, etl, databricks, gpt, 4o, from, api, dashboard, 24, transformers, text, plan, tasks, do, lists, synergy, clicks, harsanyi, dividends, commerce, 20, boosted, regression, geometry, laziness, angles, reveal, hallucinations,

Text of the page (most frequently used words):
the (29), min (28), read (28), dec (26), and (22), data (16), #learning (12), for (11), science (11), machine (10), how (10), step (8), models (7), your (6), large (6), language (6), what (6), understanding (6), with (6), about (5), tds (5), from (5), advent (5), agentic (5), programming (5), newsletter (4), angela (4), shi (4), gradient (4), calendar (4), excel (4), variable (4), use (3), why (3), agents (3), intuitive (3), pipeline (3), deep (3), optimize (3), llms (3), rag (3), they (3), search (3), latest (3), agent (3), auc (3), write (2), our (2), world (2), engineering (2), professionals (2), linkedin (2), you (2), math (2), random (2), day (2), linear (2), behind (2), harsanyi (2), real (2), application (2), management (2), look (2), transformers (2), into (2), weather (2), api (2), etl (2), dashboard (2), databricks (2), build (2), dives (2), editors (2), insights (2), art (2), better (2), most (2), python (2), using (2), think (2), metrics (2), part (2), map (2), mrr (2), ranking (2), code (2), tabpfn (2), model (2), editor (2), picks (2), all (2), has (2), same (2), towards (2), bonus (2), control (2), descent (2), systems (2), chunk (2), simple (2), jan (2), reinforcement (2), rfm (2), toggle (2), cookies, settings, terms, privacy, policy, advertise, subscribe, 2026, insight, media, group, llc, home, leading, publication, analytics, artificial, intelligence, bluesky, threads, youtube, javier, marin, story, failing, forward, spheres, can, visualize, sometimes, knows, geometry, laziness, angles, reveal, hallucinations, ensembles, optimization, boosting, explained, boosted, regression, jacob, ingle, brief, overview, dividend, synergy, clicks, dividends, commerce, kenneth, leung, process, planning, task, langchain, plan, tasks, lists, self, attention, turn, static, word, embeddings, text, gustavo, santos, guide, powered, gpt, gain, new, optimizing, workflows, making, everything, don, miss, popular, articles, past, year, 2025, must, reads, more, josiah, devalois, weekend, chore, fun, valuable, operations, research, principles, optimized, leaf, raking, strategy, stephanie, kirmer, regular, technology, users, know, product, generative, user, ida, silfverskiöld, comparing, across, datasets, running, evals, bloated, jacopo, tagliabue, make, reason, verifiable, logic, vibe, proving, marco, hening, tallarico, multiple, hypothesis, testing, values, monte, carlo, statistics, bonferroni, benjamini, hochberg, choosing, value, correction, shubham, gandhi, but, quietly, break, evaluation, here, these, fail, instead, aniruddha, karajgi, explanation, transforming, variables, correctly, keeping, probabilities, honest, jacobian, adjustment, thomas, reid, hands, tour, cprofile, snakeviz, find, fix, hot, paths, slow, stop, guessing, start, measuring, parul, pandey, architecture, training, implementing, practice, exploring, foundation, built, tabular, see, egor, howell, one, confusing, questions, tech, right, now, difference, career, advice, engineer, are, differences, eivind, kjosbakken, ensure, coding, context, facilitate, effective, lambert, leong, solution, actually, under, curve, measures, well, ranks, positives, above, negatives, independent, any, chosen, threshold, willem, esterhuizen, some, hints, good, numerics, robotics, overcoming, nonsmoothness, chattering, nonconvex, optimal, problems, momentum, rmsprop, adam, aim, minimum, not, variants, sarah, schürch, retrieval, experimenting, different, sizes, size, experimental, jasper, schroeder, five, key, learnings, that, discovered, during, challenge, apply, taught, mariya, mansurova, chat, multi, reasoning, time, rest, apis, production, ready, made, nemo, toolkit, vedant, jumle, robot, friends, collaborate, learn, fly, drone, actor, critic, method, ibrahim, salami, score, interpret, segments, eda, public, analysis, customer, segmentation, pandas, mobile, navigation, submit, article, sign, publish, global, community,

Text of the page (random words):
towards data science publish ai ml data science insights to a global community of data professionals sign in submit an article latest editor s picks deep dives newsletter write for tds toggle mobile navigation linkedin x toggle search search eda in public part 3 rfm analysis for customer segmentation in pandas data science how to build score and interpret rfm segments step by step ibrahim salami jan 1 13 min read deep reinforcement learning the actor critic method reinforcement learning robot friends collaborate to learn to fly a drone vedant jumle jan 1 19 min read latest production ready llms made simple with the nemo agent toolkit agentic ai from simple chat to multi agent reasoning and real time rest apis mariya mansurova dec 31 23 min read what advent of code has taught me about data science programming five key learnings that i discovered during a programming challenge and how they apply to jasper schroeder dec 31 10 min read chunk size as an experimental variable in rag systems large language models understanding retrieval in rag systems by experimenting with different chunk sizes sarah schürch dec 31 12 min read the machine learning advent calendar bonus 2 gradient descent variants in excel machine learning gradient descent momentum rmsprop and adam all aim for the same minimum they do not angela shi dec 31 8 min read overcoming nonsmoothness and control chattering in nonconvex optimal control problems robotics with some hints for good numerics willem esterhuizen dec 30 17 min read the machine learning advent calendar bonus 1 auc in excel machine learning auc measures how well a model ranks positives above negatives independent of any chosen threshold angela shi dec 30 8 min read agents under the curve auc agentic ai towards understanding if your agentic solution is actually better lambert leong dec 30 15 min read how to facilitate effective ai programming large language models how to ensure your coding agent has the same context as you eivind kjosbakken dec 29 7 min read machine learning vs ai engineer what are the differences career advice one of the most confusing questions in tech right now is what is the difference egor howell dec 29 7 min read see all of the latest editor s picks exploring tabpfn a foundation model built for tabular data large language models understanding the architecture training pipeline and implementing tabpfn in practice parul pandey dec 27 11 min read think your python code is slow stop guessing and start measuring programming a hands on tour of using cprofile snakeviz to find and fix the hot paths thomas reid dec 26 13 min read keeping probabilities honest the jacobian adjustment data science an intuitive explanation of transforming random variables correctly aniruddha karajgi dec 25 10 min read why map and mrr fail for search ranking and what to use instead data science map and mrr look intuitive but they quietly break ranking evaluation here s why these metrics shubham gandhi dec 25 9 min read bonferroni vs benjamini hochberg choosing your p value correction statistics multiple hypothesis testing p values and monte carlo marco hening tallarico dec 24 11 min read understanding vibe proving large language models how to make llms reason with verifiable step by step logic part 1 jacopo tagliabue dec 22 18 min read running evals on a bloated rag pipeline large language models comparing metrics across datasets and models ida silfverskiöld dec 21 71 min read understanding the generative ai user product management what do regular technology users think and know about ai stephanie kirmer dec 20 11 min read how i optimized my leaf raking strategy using linear programming data science from a weekend chore to a fun application of valuable operations research principles josiah devalois dec 19 13 min read the variable newsletter 2025 must reads agents python llms and more the variable don t miss our most popular articles of the past year tds editors dec 18 5 min read tds newsletter optimize optimize optimize or the art of making everything better the variable gain new insights into the art of optimizing your data science and ml workflows tds editors dec 11 3 min read deep dives how to build an ai powered weather etl pipeline with databricks and gpt 4o from api to dashboard data engineering a step by step guide from weather api etl to dashboard on databricks gustavo santos dec 26 11 min read the machine learning advent calendar day 24 transformers for text in excel machine learning an intuitive step by step look at how transformers use self attention to turn static word embeddings into angela shi dec 24 11 min read how agents plan tasks with to do lists agentic ai understanding the process behind agentic planning and task management in langchain kenneth leung dec 23 7 min read synergy in clicks harsanyi dividends for e commerce data science a brief overview of the math behind the harsanyi dividend and a real world application in jacob ingle dec 23 19 min read the machine learning advent calendar day 20 gradient boosted linear regression in excel machine learning from random ensembles to optimization gradient boosting explained angela shi dec 22 11 min read the geometry of laziness what angles reveal about ai hallucinations large language models a story about failing forward spheres you can t visualize and why sometimes the math knows javier marin dec 22 12 min read youtube x linkedin threads bluesky your home for data science and al the world s leading publication for data science data analytics data engineering machine learning and artificial intelligence professionals insight media group llc 2026 subscribe to our newsletter write for tds about advertise privacy policy terms of use cookies settings