iiinova — where your digital self keeps evolving

Philipp Bach

@philippbach.bsky.social

Assistant Professor (Juniorprofessor) of Econometrics; FU Berlin; Interests: Causal machine learning, causality, data science, statistics, econometrics ; philippbach.github.io

Posts Replies Media

Philipp Bach @philippbach.bsky.social · 08/12/2025

📣 Announcing the First DoubleML User Survey! 📊 We’re excited to launch the first DoubleML User Survey! We’d love to hear from all prospective, new, or experienced users of DoubleML in Python or R. 🔗Please take part here: forms.gle/HjZsWgrF5UEF... #EconSky #CausalSky #dataSkyence #Python #R

The DoubleML rhino shouting out "User Survey", available via https://forms.gle/HjZsWgrF5UEFUyDX9

122

Philipp Bach @philippbach.bsky.social · 06/01/2025

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 · 06/01/2025

🆕 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

Philipp Bach @philippbach.bsky.social · 05/02/2024

🚀 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