Data Scientist
Kansas City
Joined January 2014
- Tweets134
- Following102
- Followers91
- Likes34
Today the @tru_factor #DataScience posted datasets in @awscloud Data Exchange to help #COVID19 #researchers understand how mobility patterns have changed in the US. Get the datasets: go.aws/2UoEloz and go.aws/3dyjYwJ. Get code here bit.ly/2QPoOfy.
Matt Habiger retweeted
@tru_factor's technology provides fine-grained data on population movements to analytics companies, who in turn can generate insights that would otherwise be prohibitively expensive for small governments bit.ly/2JmflIH #govtech #stateandlocal #data @MattHabiger
Matt Habiger retweeted
TruFactor, partners bring marketing-type data to government bit.ly/2JmflIH #govtech #stateandlocal #data @tru_factor @MattHabiger
Was a fun interview and looking forward to helping more companies in the #govtech #urban_planning space.
This Post is from an account that no longer exists. Learn more
2
Matt Habiger retweeted
What machine learning commentators talk about: deep neural net flavor du jour, AI risk
What machine learning practitioners talk about: messy data, data labeling, tuning learning rates, collecting more data, feature representation, cost functions, latency, productionization, ...
Looking to prove/disprove correlation of two time series. Suppose x and y have the same feature set z. And x and y have mild correlation, say 0.6. However, I believe z causes x and y to be correlated. Regress x on z and y on z then compare correlation of errors, no?
Matt Habiger retweeted
We're looking for great people to join the Replica team! Hiring for several positions in KC and SF. If you're passionate about helping cities solve challenging transportation and land use issues, come jam with us. replicahq.com/#jobs-section
Matt Habiger retweeted
Its economy is the largest in the world and grew at a rate of 4.1 percent last quarter, its fastest pace since 2014.
bloomberg.com/graphics/2018-…
Matt Habiger retweeted
Released 0.3 dtreeviz! Adds uni- and bivariate feature-target space visualizations to show feature space tessellations resulting from decision trees. `pip install -U dtreeviz` Code samples at repo: github.com/parrt/dtreeviz
Matt Habiger retweeted
📊📈📉👉Data Fallacies to Avoid — An Illustrated Collection of Mistakes that People Often Make When Analyzing Data: bit.ly/2pPnUSu #abdsc #BigData #Analytics #DataScience #Statistics #DataLiteracy #DataEthics #DataScientists #StatisticalLiteracy
Matt Habiger retweeted
Data Scientists at @getfreebird like @colindcarroll regularly present on topics like "Visualizing Uncertainty" at industry conferences like @PyData, the statistical science behind getting disrupted travelers where they need to be, colcarroll.github.io/arviz_p…
Away we go!
Myself and the rest of the @PinsightMedia team are excited to join the @InMobi family! #DataDriven
inmobi.com/inmobi-acquires-p…
1
Matt Habiger retweeted
We use @awscloud to increase our computing power to best deliver solutions to our customers. Check out the case study here: ow.ly/VmAp30kVjCD
Matt Habiger retweeted
Woah: @pandoramusic has been running a *massive* RCT to see how the # of ads we hear affects how long we listen.
Finding: more ads means a lot less listening + more premium upgrades (especially for older people).
#SocSciResearch
bit.ly/2HYplpw
Check out this Meetup: Time-Frequency Analysis of Music meetup.com/Data-Science-KC/e… #Meetup #DSKC #KansasCity via @Meetup
Matt Habiger retweeted
In order for brands and marketers to connect in a lasting way, experiences must feel authentic and tailored to a segment of one. ow.ly/QEp130japjM
Matt Habiger retweeted
The Next Endangered Species Is the American Hunter | Field & Stream fieldandstre.am/KSjVCv via @fieldandstream
Matt Habiger retweeted
Playing around with trying to visualize the learned context vector of the attention mechanism in @spacy_io's text classifier using @TensorFlow's embeddings projector: justindujardin.github.io/pro…