Essential Guide: Datascience - Comprehensive Guide

👋 Sign in for the ability to sort posts by relevant, latest, or top.

munimv2

Nov 2

MMLU-Pro still uses the MMLU answer keys that experts flagged as wrong on 52 of 55 questions

#machinelearning #datascience #nlp #benchmarks

4 min read

十方空烬 · Ember ☄️

Nov 2

Reviewing accepted items does not reveal what a filter missed

#python #testing #datascience

2 min read

Bot LAB

Nov 2

Paper Trading Crypto Futures: How to Make It Honest

#trading #crypto #datascience #beginners

7 min read

Outfame Team

Nov 2

5 rules we used to turn 164,963 daily follower readings into one honest growth number

#datascience #analytics #sql #statistics

3 min read

Daniel Oliveira

Nov 2

I read every AI claim on 4,335 earnings calls. A keyword filter would have got most of them wrong

#datascience #python #ai #nlp

5 min read

proxyvero

Nov 2

We Tested 82 Residential Proxy Providers Across 142,310 Real-World Requests: October 2026 Report

#webscraping #python #datascience #benchmark

6 min read

Jukka Blomberg

Nov 2

The day before the US midterms, three separate Polymarket markets agree with each other to within half a point

#python #datascience #api #opendata

2 min read

UpGrow Team

Nov 2

Instagram follower counts across 1,064,485 accounts: median 214, 78.9% under 1,000

#datascience #analytics #socialmedia #statistics

3 min read

Tabletop Dev Labs

Nov 1

Quantifying Game Complexity: A Data-Driven Analysis of Board Games with Python & LLMs

#datascience #python #gamedev #ai

3 min read

MedAnnotate

Nov 2

Why Expert Medical Data Annotation Matters for Healthcare AI

#healthcare #ai #machinelearning #datascience

2 min read

munimv2

Nov 1

I ranked 5,054 DEV challenge entries before the winners were named. Here is how it went

#discuss #devchallenge #datascience #writing

7 min read

Jason Lau

Nov 1

Your Churn Model Works. Your Churn Intervention Doesn't.

#machinelearning #causalinference #churn #datascience

11 min read

Tan Tran

Nov 1

Peeking at your A/B test turns 5% false positives into 25%, and what mSPRT costs you

#datascience #statistics #abtesting #python

8 min read

Umesh Tharuka Malaviarachchi

Nov 1

Amortised Inference: Why Training a Network to Infer Beats Running Optimisation Every Time

#machinelearning #datascience #ai #statistics

7 min read

Quantooox

Nov 1

Out of how many? Multiple testing and the deflated Sharpe ratio

#statistics #datascience #machinelearning #beginners

2 min read

👋 Sign in for the ability to sort posts by relevant, latest, or top.

DEV Community

Data Science

MMLU-Pro still uses the MMLU answer keys that experts flagged as wrong on 52 of 55 questions

Reviewing accepted items does not reveal what a filter missed

Paper Trading Crypto Futures: How to Make It Honest

5 rules we used to turn 164,963 daily follower readings into one honest growth number

I read every AI claim on 4,335 earnings calls. A keyword filter would have got most of them wrong

We Tested 82 Residential Proxy Providers Across 142,310 Real-World Requests: October 2026 Report

The day before the US midterms, three separate Polymarket markets agree with each other to within half a point

Instagram follower counts across 1,064,485 accounts: median 214, 78.9% under 1,000

Quantifying Game Complexity: A Data-Driven Analysis of Board Games with Python & LLMs

Why Expert Medical Data Annotation Matters for Healthcare AI

I ranked 5,054 DEV challenge entries before the winners were named. Here is how it went

Your Churn Model Works. Your Churn Intervention Doesn't.

Peeking at your A/B test turns 5% false positives into 25%, and what mSPRT costs you

Amortised Inference: Why Training a Network to Infer Beats Running Optimisation Every Time

Out of how many? Multiple testing and the deflated Sharpe ratio