Tag

#datascience

177 posts29 followers

Explore Hashnode

Alternatives

Arnold Holm10h ago · 5 min read

95% had no second funded account: keep four counters in your simulation

If you model reinvested payouts, count the steps before counting the next account. About 95% of the paths in our 24-month model never reached a second funded account. We simulated 20,000 paths startin

stratcorealpha.hashnode.dev

Groundplane Labs3d ago · 3 min read

Pulling restaurant health inspection data via API (9 US jurisdictions, JSON out)

Restaurant health inspection results are public almost everywhere in the US, but every county publishes them differently: Socrata APIs, ArcGIS layers, CSV dumps, or a search form that only shows one p

groundplanes.hashnode.dev

Kelyn NjeriOct 7 · 15 min read

except Exception: pass hid a dead causal engine

For 158 days, the part of NeoRx that made it a causal system called a function that doesn't exist. nx.d_separated was removed from NetworkX in 3.5, released May 2025, and NeoRx has pinned 3.6.1 since

mindstate.hashnode.dev

gold365nameOct 5 · 4 min read

Implementing Secure Session Management & Rate Limiting for Live Sports Dashboards in Python

Real-time sports intelligence platforms handle high-concurrency traffic bursts, especially during live match crunch moments and tournament finals. While software engineers focus extensively on reducin

gold365insights.hashnode.dev

gold365nameOct 5 · 3 min read

Architecting a Real-Time Cricket Telemetry Pipeline with Python and WebSockets

In modern sports engineering, capturing live match dynamics requires high-throughput data pipelines capable of processing sub-second event feeds. Cricket presents a complex state environment where eve

gold365insights.hashnode.dev

DRM3Sep 30 · 2 min read

How to find trusted datasets for AI

There is no shortage of datasets. There is a shortage of datasets you can put in production and defend when someone asks where a number came from. The gap between the two is provenance. Start with dis

drm3.hashnode.dev

Faith MwendeSep 29 · 3 min read

Splitting Fraud Data Without Breaking the Ratio (Day 3)

Day 1 was setup. Day 2 was looking at the data. Day 3 was the first real modeling decision: how do I split this data without breaking it? The problem it solves You can't train a model on all your data

beginnerslog.hashnode.dev

Faith MwendeSep 27 · 3 min read

What I Learned From My First Look at Fraud Data (Day 2)

Day 1 was setup. Day 2 was the first time I actually looked at the data and the numbers immediately broke my assumptions. Here's what the credit card fraud dataset told me. The problem it solves I had

beginnerslog.hashnode.dev

Michael HairetisSep 26 · 5 min read

A Forecasting Model That Correctly Refuses to Forecast

It beat the baseline by 98.7% on one series and lost to repeating the last value on another. That contrast is the most useful single fact about it. Part one covered what TimesFM 3.0 is: a stateless n

1 openred.hashnode.dev

Vivek BiswasSep 21 · 30 min read

Days 6-14: From Corporate Actions to My First Full Annual Report, the Complete Week 2 Recap

Day 6: Asset Turnover, Cash Cycles, and What Corporate Actions Actually Do to Your Shares Today was a concept-heavy day, four new ideas back to back, and for the first time I actually needed a table t

zero2ds.hashnode.dev

Search Hashnode

Explore Hashnode

Trending tags this week

95% had no second funded account: keep four counters in your simulation

Pulling restaurant health inspection data via API (9 US jurisdictions, JSON out)

except Exception: pass hid a dead causal engine

Implementing Secure Session Management & Rate Limiting for Live Sports Dashboards in Python

Architecting a Real-Time Cricket Telemetry Pipeline with Python and WebSockets

How to find trusted datasets for AI

Splitting Fraud Data Without Breaking the Ratio (Day 3)

What I Learned From My First Look at Fraud Data (Day 2)

A Forecasting Model That Correctly Refuses to Forecast

Days 6-14: From Corporate Actions to My First Full Annual Report, the Complete Week 2 Recap