juanitorduz
@juanitorduz.bsky.social
๐ค 326
๐ฅ 376
๐ 129
Applied Scientist | Math PhD | Open Source PyMC Labs
https://juanitorduz.github.io
Here are two examples on causal inference and through the lens of probabilistic programming languages (PPLs): - Introduction to Causal Inference with PPLs
juanitorduz.github.io/intro_causal...
- Causal Inference with Multilevel Models:
juanitorduz.github.io/ci_multilevel/
Implementations in PyMC.
loading . . .
LinkedIn
This link will take you to a page thatโs not on LinkedIn
https://lnkd.in/de58y5vB
21 days ago
0
4
1
Here is the recording of my talk PyData Berlin 2025: Introduction to Stochastic Variational Inference with NumPyro Notebook:
juanitorduz.github.io/intro_svi/
youtu.be/wG0no-mUMf0?...
#pydata
#berlin
#bayes
loading . . .
Scaling Probabilistic Models with Variational Inference
YouTube video by PyData
https://youtu.be/wG0no-mUMf0?si=MOf5NdzqBLvaTMN9
27 days ago
0
12
4
reposted by
juanitorduz
Noam Ross
11 months ago
Open Science and Open Source only with Diversity, Equity, Inclusion and Accessibility. Inclusion is essential to science, and science is only worthwhile if it lifts everyone up together.
ropensci.org/blog/2025/02...
#OpenSource
#OpenScience
loading . . .
Open Science and Open Source only with Diversity, Equity, Inclusion, and Accessibility
Including all of humanity is and always will be at the heart of open science.
https://ropensci.org/blog/2025/02/05/no-science-without-deia/
0
100
41
I got mail! I canโt not wait
@vincentab.bsky.social
Iโll try to do many of these examples by โhandโ (learning by doing).
2 months ago
1
8
1
reposted by
juanitorduz
Andrew Gelman et al.
2 months ago
7 reasons to use Bayesian inference!
statmodeling.stat.columbia.edu/2025/10/11/7...
loading . . .
7 reasons to use Bayesian inference! | Statistical Modeling, Causal Inference, and Social Science
https://statmodeling.stat.columbia.edu/2025/10/11/7-reasons-to-use-bayesian-inference/
1
28
14
It was fun (painful ๐ ) to implement VAR(p) models from scratch
juanitorduz.github.io/var_numpyro/
loading . . .
Bayesian Vector Autoregressive Models in NumPyro - Dr. Juan Camilo Orduz
https://juanitorduz.github.io/var_numpyro/
3 months ago
1
14
3
Festival der Riesendrachen
#Berlin
3 months ago
0
4
0
reposted by
juanitorduz
Gabriel Stechschulte
3 months ago
Reproducing Uber's Alternating Direction Method of Multipliers (ADMM) based automated budget allocation system in JAX
gstechschulte.github.io/posts/2025-0...
loading . . .
Reproducing Uber's Marketplace Optimization
Uber allocates money across different regions and programs to incentivize riders and drivers to use Uber products. This incentive structure ultimately influences the market. This leads to the natural ...
https://gstechschulte.github.io/posts/2025-09-15-marketplace-optimization/
0
3
1
reposted by
juanitorduz
Jan Boelts
3 months ago
Kudos to
@sethaxen.com
for implementing the Pyro wrapper that makes this possible (shipped in sbi v0.25)! And thanks to
@juanitorduz.bsky.social
sharing the cookie factory exampleโit's a great accessible example for hierarchical inference. Everything runs in Colab ๐
0
4
1
reposted by
juanitorduz
Chris Fonnesbeck
3 months ago
A nice primer on normalizing flows by PyMC/PyTensor devs Ricardo and Jesse.
pytensor.readthedocs.io/en/latest/ga...
loading . . .
Normalizing Flows in PyTensor โ PyTensor dev documentation
https://pytensor.readthedocs.io/en/latest/gallery/applications/normalizing_flows_in_pytensor.html
0
4
3
Here are the materials for the PyData Berlin 2025 talk on Stochastic Variational Inference with NumPyro: - Slides:
juanitorduz.github.io/html/intro_s...
- Notebook;
juanitorduz.github.io/intro_svi/
loading . . .
Scaling Probabilistic Models with Variational Inference
https://juanitorduz.github.io/html/intro_svi.html
3 months ago
0
2
0
The ArviZ core devs have done tremendous work on an improved API with a lot of novel improvements. They have put together a great migration guide:
python.arviz.org/en/stable/us...
If you are an ArviZ user please take a look at it and provide feedback. Open source is all about the community ๐ซถ
loading . . .
LinkedIn
This link will take you to a page thatโs not on LinkedIn
https://lnkd.in/dxQfwEtr
5 months ago
0
7
3
Los Amigos Invisibles
#Berlin
6 months ago
0
1
0
Iโll be giving a talk ok variational inference (VI) at PyData Berlin 2025 ๐! Iโll focus on some learnings of using VI for forecasting models at scale. If you are around come and say hi.
#PyDataBerlin
6 months ago
0
3
0
I used to experience this and it is fucking horrible ๐ซ
add a skeleton here at some point
6 months ago
0
1
0
A beautiful read!
@markhoppus.bsky.social
#blink182
7 months ago
0
0
0
reposted by
juanitorduz
PyMC Labs
8 months ago
Forecasting isnโt just about prediction โ itโs about decision-making under uncertainty.
@juanitorduz.bsky.social
shows how Bayesian models help: ๐น Sparse data? Use hierarchies ๐น Stockouts? Use censored likelihoods ๐น Messy demand? Use priors + state spaces Practical guide ๐
dub.sh/prob-forecas...
loading . . .
Probabilistic Time Series Analysis: Opportunities and Applications - PyMC Labs
https://dub.sh/prob-forecasting
0
7
3
reposted by
juanitorduz
Ursula von der Leyen
8 months ago
Freedom of science and research is one of Europe's great strengths. Itโs how excellence and innovation thrive. Weโll make proposals to help scientists and researchers โChoose Europeโ. The best and brightest from around the world. โจ To make Europe the home of innovation again. โ
europa.eu/!JFF7jm
45
1233
300
Here is a first intro notebook on Bayesian Power Analysis following the method described in the paper "The Bayesian New Statistics: Hypothesis testing, estimation, meta-analysis, and power analysis from a Bayesian perspective" (
link.springer.com/content/pdf/...
)
juanitorduz.github.io/power_sample...
loading . . .
Introduction to Bayesian Power Analysis: Exclude a Null Value - Dr. Juan Camilo Orduz
https://juanitorduz.github.io/power_sample_size_exclude_null/
8 months ago
0
7
1
Here is a new blog post withย PyMC Labs: "Probabilistic Time Series Analysis: Opportunities and Applications." We provide a collection of business cases where probabilistic methods excel in real-world applications of probabilistic time series methods.
www.pymc-labs.com/blog-posts/p...
loading . . .
Probabilistic Time Series Analysis: Opportunities and Applications - PyMC Labs
https://www.pymc-labs.com/blog-posts/probabilistic-forecasting/
8 months ago
0
1
0
I decided to wrap these cohort modeling techniques in a little pre-print ๐ค
arxiv.org/abs/2504.16216
loading . . .
Cohort Revenue & Retention Analysis: A Bayesian Approach
We present a Bayesian approach to model cohort-level retention rates and revenue over time. We use Bayesian additive regression trees (BART) to model the retention component which we couple with a lin...
https://arxiv.org/abs/2504.16216
8 months ago
0
0
0
reposted by
juanitorduz
Allen Downey
8 months ago
Time Series Analysis with StatsModels Video from my PyData Global tutorial is up now:
www.youtube.com/watch?v=foMb...
loading . . .
Allen Downey - Time Series Analysis with StatsModels | PyData Global 2024
YouTube video by PyData
https://www.youtube.com/watch?v=foMbacbuAQk
0
10
5
reposted by
juanitorduz
Rob Hyndman
8 months ago
A new Python edition of "Forecasting: Principles and Practice" is now available online at
otexts.com/fpppy/
. Thanks to
@azulgarza.bsky.social
, Cristian Challu, Max Mergenthaler, Kin Olivares & Nixtla for making this happen.
#forecasting
#python
loading . . .
Forecasting: Principles and Practice, the Pythonic Way
https://otexts.com/fpppy/
3
81
27
reposted by
juanitorduz
Vincent Arel-Bundock
8 months ago
๐๐ ๐ Yay!! I just submitted the complete manuscript of my upcoming book to the publisher! Learn to easily and clearly interpret (almost) any stats model w/ R or Python. Simple ideas, consistent workflow, powerful tools, detailed case studies. Read it for free @
marginaleffects.com
#RStats
#PyData
21
594
157
This is my current readingI had it in my mind for many years and I finally decided to read it! So far so good!
9 months ago
0
2
0
Iโll be attending the 3rd Vienna Workshop on Economic Forecasting 2025 where I will have a poster on โProbabilistic Forecasting at Scale with NumPyroโ ๐
www.ihs.ac.at/current/even...
loading . . .
Vienna Workshop on Economic Forecasting 2020
The submission deadline for the 2nd Vienna Workshop on Economic Forecasting has been extended to August 31st.
https://www.ihs.ac.at/current/events/conference-series/forecasting-workshop/vienna-workshop-on-economic-forecasting-2025/
9 months ago
0
1
0
reposted by
juanitorduz
Allen Downey
9 months ago
At PyMC Labs I've been working with a group developing synthetic consumers for marketing research. We just published this white paper with an overview of work in this space -- and we have a blog post coming next week with some experimental results.
www.pymc-labs.com/blog-posts/s...
loading . . .
Synthetic Consumers: The Promise, The Reality, and The Future - PyMC Labs
https://www.pymc-labs.com/blog-posts/synthetic-consumers/
0
8
3
reposted by
juanitorduz
PyMC Labs
9 months ago
We just launched our first white paper! By 2027, AI-generated consumers could power 50%+ of market research data. ๐ Whatโs inside? โ What synthetic consumers are โ How businesses use them and more.... ๐
dub.sh/61AEavU
๐ฉ Curious how this could benefit your org? ๐
[email protected]
#GenAI
0
5
2
We just released PyMC-Marketing with a new multidimensional MMM class to allow for custom hierarchical model across multiple dimensions (e.g. geographies). You can specify hierarchical components easily so the opportunities are huge.
www.pymc-marketing.io/en/stable/no...
#mmm
#pymc
#marketing
9 months ago
1
7
1
reposted by
juanitorduz
Gaรซl Varoquaux
9 months ago
Open source is draining. One's todo-list is open to world. People seldom realize the cost of what they get for free. Unpleasant comments do happen. Cost of maintenance is not understood.
opensource.com/article/17/2...
3
70
19
reposted by
juanitorduz
Demetri
9 months ago
It was suggested by
@juanitorduz.bsky.social
that I add some simulation proof to some claims I make in my blog post over at
geteppo.com
By all means, have some simulation proof (plus a little explanation of what I said re: pulling estimates apart)
dpananos.github.io/posts/2025-0...
loading . . .
Demetri Pananos Ph.D - More on Bayesian Statistics
https://dpananos.github.io/posts/2025-03-17-bayes-big-deal/
1
16
2
reposted by
juanitorduz
Gaรซl Varoquaux
9 months ago
๐ฅ๐New library: boosting for survival analysis, including multiclass (competing risks) Survival = missing outcomes because limited observation window (common in medicine, marketting...)
soda-inria.github.io/hazardous
Gives very fast boosted-trees for survival
1
45
11
reposted by
juanitorduz
Aki Vehtari
10 months ago
My favorites: Challenges and opportunities...
proceedings.neurips.cc/paper/2021/h...
Robust, accurate stochastic optimization...
papers.nips.cc/paper/2020/h...
...improving the reliability of black-box VI
jmlr.org/papers/v25/2...
Yes, but Did It Work? ...
proceedings.mlr.press/v80/yao18a.h...
1
4
1
Hi! Here is a question for all the
#bayesian
folks! Can you recommend references on evaluation and diagnostics of (stochastic) variational inference? Anything would be much appreciated ๐
10 months ago
1
2
1
reposted by
juanitorduz
JD Long
10 months ago
add a skeleton here at some point
0
8
1
reposted by
juanitorduz
Peter Tennant
11 months ago
"Have directed acyclic graphs fullfilled their promise?" - the recording of my debate with
@margaritamb.bsky.social
at the World Congress of Epidemiology 2024 is now available on YouTube!
www.youtube.com/watch?v=FG79...
#EpiSky
#CausalSky
#WCE2025
loading . . .
WCE2024 - INT02 - Debate - Have DAGS fulfilled their promise?
YouTube video by World Congress of Epidemiology 2024
https://www.youtube.com/watch?v=FG79SR-zQbI
9
74
22
reposted by
juanitorduz
PyMC Labs
10 months ago
๐๐ฒ๐๐-๐๐๐ซ๐ค๐๐ญ๐ข๐ง๐ ๐ข๐ฌ ๐ ๐ซ๐จ๐ฐ๐ข๐ง๐ ๐๐๐ฌ๐ญ. Weโve crossed 175,000 ๐ญ๐จ๐ญ๐๐ฅ ๐๐จ๐ฐ๐ง๐ฅ๐จ๐๐๐ฌ & now hit 20,000 ๐ฆ๐จ๐ง๐ญ๐ก๐ฅ๐ฒ ๐๐จ๐ฐ๐ง๐ฅ๐จ๐๐๐ฌ. ๐ค๐๐ก๐ข๐ง๐ค๐ข๐ง๐ ๐จ๐ ๐๐ฎ๐ข๐ฅ๐๐ข๐ง๐ ๐๐ง-๐๐จ๐ฎ๐ฌ๐? Developing a custom solution can take ๐ฆ๐จ๐ง๐ญ๐ก๐ฌ, ๐๐ฒ๐๐-๐๐๐ซ๐ค๐๐ญ๐ข๐ง๐ gets you there ๐๐๐ฌ๐ญ๐๐ซ ๐ ๐๐๐ก๐๐๐ฎ๐ฅ๐ ๐ ๐ ๐ซ๐๐ ๐๐ญ๐ซ๐๐ญ๐๐ ๐ฒ ๐๐จ๐ง๐ฌ๐ฎ๐ฅ๐ญ๐๐ญ๐ข๐จ๐ง :
calendly.com/niall-oulton
0
9
3
PyMC-Marketing 0.11.0 is out! It is a huge release with more than 80 PRs from the community ๐. Checkout the release notes:
github.com/pymc-labs/py...
loading . . .
Release 0.11.0 ยท pymc-labs/pymc-marketing
What's Changed Major Changes ๐ Bump pymc dependency by @ricardoV94 in #1269 Budget optimizer refactor by @ricardoV94 in #1357 New Features ๐ add hdi_list kwarg to plot_posterior_predictive by @d...
https://github.com/pymc-labs/pymc-marketing/releases/tag/0.11.0
11 months ago
0
3
0
reposted by
juanitorduz
Kevin McShane (Verified)
11 months ago
"Masculine Energy"
272
40286
9531
Its much more pleasant to write a latex article with a linter, git, girhub actions, and LLMs thank in a simple tex editor (10 years ago ๐ )
11 months ago
0
2
0
reposted by
juanitorduz
Jess Rohmann
11 months ago
We're looking to connect Berlin & Brandenburg researchers working with causal graphs from all disciplines! โก๏ธ "Direct" link:
applied-causal-graphs.de
โฌ ๏ธ โฑ๏ธ Abstracts due Feb 7th!
#CausalInference
#DAGs
#Berlin
#CausalGraphs
โญ Keynotes by
@philippbach.bsky.social
@pwgtennant.bsky.social
& Simone Maxand
2
34
21
I hate everything about Meta ๐.
11 months ago
0
2
0
Classic Meta being Meta.
12 months ago
0
1
0
reposted by
juanitorduz
PyMC Labs
12 months ago
โจ This year, we saw many new contributors contribute to PyMC-Marketing & CausalPy. Their work has made a real difference. ๐ฑ Some are first-time contributors, while others are experienced developers. ๐ Thank you to everyone who contributed this year weโre excited to see whatโs next!
loading . . .
0
5
3
Working with together Claude and exploring JAX internals to write the demean step (alternating projections algorithm) for PyFixEst! The first experiments on GPU show potential against the current numba implementation. The PR is is still open for comments and feedback
github.com/py-econometr...
12 months ago
1
3
0
I have decided to collect talk recordings and slides in the same place ๐
juanitorduz.github.io/talks/
loading . . .
Talks - Dr. Juan Camilo Orduz
https://juanitorduz.github.io/talks/
about 1 year ago
0
3
0
Yesterday I gave a summary talk on probabilistic forecasting: opportunities and applications Next year Iโll continue experimenting and sharing more around these topics ๐
juanitorduz.github.io/html/paretos...
loading . . .
Probabilistic Time Series Forecasting
https://juanitorduz.github.io/html/paretos/probabilistic_forecasting#/title-slide
about 1 year ago
0
4
1
I have been using Pydantic for more than a year and Pandera for around 8 months for data validation and it has made my data workflow so much better! Totally recommended!
about 1 year ago
0
0
0
No sleep, sick child, fever, clients call, pull requests, rainy days, slackโฆ
#parenthood
about 1 year ago
0
3
0
reposted by
juanitorduz
PyMC Labs
about 1 year ago
๐ฅ The
@pydata.bsky.social
NYC talk by Christian Luhmann on ๐๐ฒ๐๐-๐๐๐ซ๐ค๐๐ญ๐ข๐ง๐ is now live on Youtube! ๐ Catch the replay and see how Bayesian modelling simplifies complex analytics! ๐
youtu.be/4FznIhcrHCA?...
#PyMCMarketing
#Bayesian
loading . . .
0
12
4
Load more
feeds!
log in