iiinova — where your digital self keeps evolving

The paper is joint work with (I guess almost all bsky-less) Victor Chernozhukov @svenklaassen.bsky.social Martin Spindler Jan Teichert-Kluge Suhas Vijaykumar Looking forward to your thoughts, comments and questions!

100

The causal part: If you are a #causal #DAG enthusiast, you'll finde some causal diagrams and a discussion on causal aspects of demand analysis in the paper too 😀 #CausalSky #dataSkyence

100

The fun part (that's what you usually don't read in the papers): Embedding text and image data makes demand analysis pretty accessible from an intuitive point of view. You can play around with the product embeddings, check for similarities and formulate/check hypotheses for various demand patterns

Our learnings: We find that text and image data play an important role in predictive and causal demand analysis: Improved demand prediction and advanced heterogeneity analysis using product infos encoded in text and images, e.g., based on similarities and AI/data-driven product categorization.

100

Our approach: 1️⃣ Enhanced Predictions: AI-driven embeddings significantly improve the accuracy of sales rank and price predictions 2️⃣ Improved Causal Inference: By fine-tuning embeddings for causal tasks, we uncover strong heterogeneity in price elasticity linked to product-specific features

Table 5 from the referenced paper showing the predictive performance of various models used for demand analysis. Deep learning based approaches that utilize both image & text data are found to substantially better predict the quantity and price signals than traditional (linear regression with tabular features only) and ML learners (boosted trees with tabular features)

A sorted-effects plot summarizing the heterogeneity in price elasticities as obtained from AI-based heterogeneity analysis (three different model specifications). More information, see Figure 7 in the linked paper.

120

Philipp Bach @philippbach.bsky.social · 19/11/2024

🆕 New year, new working paper: Adventures in Demand Analysis using AI 🆕 Our question: How can we advance demand analysis using recent tools from AI (Deep Learning, LLMs etc)? Our idea: Use information from text & images in digital marketplaces like Amazon Paper: arxiv.org/abs/2501.00382 #EconSky

An AI-generated image showing a red and blue toy car with eyes. The figure has been obtained from summarizing a product category called "Iconic Movie-Inspired 1:55 Scale Diecast Cars Perfect for Storytelling
and Roleplay". The categorization has been obtained in the referenced paper. More details in Table 4.

142

This looks like a pretty useful paper and - probably more importantly - a pretty useful practical procedure to find our what happens when running Causal Machine Learning. Balancing checks etc are common in traditional approaches (like PSM), but are usually mor tricky to assess in ML-based estimation

151

Reposted by Philipp Bach

Paul Hünermund @p-hunermund.com · 15/11/2024

I'm trying to compete with @stephenjwild.bsky.social's DAG People starter pack, because economists believe in competition Open to suggestions! go.bsky.app/Fa2XSDH

159134

Reposted by Philipp Bach

Martin Huber @causalhuber.bsky.social · 26/04/2024

Join our team at the Econ Department of Uni Fribourg! We're hiring for a Post-doc position and a Ph.D. position in an SNF-funded project on #NetworkScience & #Economics, led by Berno Büchel (visit berno.info). Duration: 40 months. #PostDoc #JobOpening #EconSky

043

Philipp Bach @philippbach.bsky.social · 08/02/2024

Regarding the Riesz representers: we have the analytical RRs implemented for the sensitivity part, but the data driven RR are still to be added. That's a bit experimental and not 100% clear how to integrate them in the package

020

Philipp Bach @philippbach.bsky.social · 08/02/2024

Haha thanks. We haven't planned to include it in DoubleML yet, but maybe that's a good idea. Yes we are working on the RR too, but that may still take some time. Thanks 😊

100

In case you like to learn more about the ideas behind all these new features, join our DoubleML trainings: trainings.doubleml.org Next training starts in March: doubleml-training-mar-2024.eventbrite.de #EconSky

000

3. Python API Updates: - Added Utility Classes and Functions: docs.doubleml.org/stable/api/a...

100

2. Multiple new examples: docs.doubleml.org/stable/examp... - First Stage and Causal Estimation Notebook - Basic IV Notebooks for Python and R - GATE and CATE Notebooks für PLR - GATE Sensitvity Notebook (for IRM or weighted average treatment effects)

100

1. Updated Userguide: - GATE and CATE for PLR: docs.doubleml.org/stable/guide... - Weighted Average Treatment Effects: docs.doubleml.org/stable/guide... - External predictions: docs.doubleml.org/stable/guide... - Updated description of Sensitvity Analysis (IRM): docs.doubleml.org/stable/guide...

100

Philipp Bach @philippbach.bsky.social · 11/01/2024

🚀 New release of DoubleML with new features and much more documentation for practical applications🚀 Thanks a lot to @svenklaassen.bsky.social made most of the changes 🙏 New changes (more info below): 1. Updated Userguide 2. Several new Examples on how to use DoubleML 3. Updates to the Python API

130

That's great, thank you! I was waiting for this already for some time ;) it's a great book

000

Reposted by Philipp Bach

Martin Huber @causalhuber.bsky.social · 19/12/2023

Exciting update on my book #CausalAnalysis: Now, many empirical examples initially available for the software #R are also provided as #Python code! Download them for free from the following website: www.unifr.ch/appecon/en/r... #EconSky

unifr.ch

Text book "Causal Analysis" | Chair of Applied Econometrics and Policy Evaluation | University of F...

1105

Philipp Bach @philippbach.bsky.social · 18/12/2023

We give this course together with @svenklaassen.bsky.social and (blueskyless) Martin Spindler. This training is organized in cooperation with Economic AI.

000

Philipp Bach @philippbach.bsky.social · 18/12/2023

If you have questions, feel free to reach out to us: either via dm or email to trainings@economicai.com #doubleml #causalml #causalai #ai #machinelearning #pricing #marketing #abtesting #experimentation #upliftmodelling #personalization

100

Philipp Bach @philippbach.bsky.social · 18/12/2023

2024 we offer three editions of our 2-day course "Causal Machine Learning with DoubleML" for Data Scientists, Analysts and Researchers. More information can be found here: trainings.doubleml.org #causality #EconSky

111

Philipp Bach @philippbach.bsky.social · 17/11/2023

... Klosin & Vilgalys (2022) arxiv.org/abs/2207.08789 . The last two have a somewhat different focus w.r.t. to heterogeneous treatment effects and auto-debiased learning . Other than those, I'm not aware of real "application" papers... the mentioned papers all have some focus on the overall approach

Philipp Bach @philippbach.bsky.social · 17/11/2023

Thanks. svenklaassen.bsky.social and I can add the following papers: Zimmert (2020) arxiv.org/pdf/1809.016... & Chang (2020) doi.org/10.1093/ectj... with DiD settings; some papers that consider panel settings are also Semenova et al. (2023) doi.org/10.3982/QE1670 and ...

Philipp Bach @philippbach.bsky.social · 08/11/2023

The implementation of the cluster cross-fitting algorithm is pretty general in DoubleML (Python & R) , so maybe that helps you to get it run... also I didn't want to miss the chance to also invite @svenklaassen.bsky.social to this discussion :)