8000 JanaJarecki (Jana B Jarecki (PhD)) · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content
View JanaJarecki's full-sized avatar

Block or report JanaJarecki

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
janajarecki/README.md

I develop statistical and machine learning models to forecast individual behavior in complex, real-world settings — drawing on over 14 years of research in cognition, decision-making, and learning, and over 10 years of experience with empirical modeling, coding, and behavioral data analysis.

My focus is on high-dimensional, longitudinal, and multi-modal data: sensor signals, digital traces, experimental and observational datasets, EHRs, choice tasks, A/B tests, and usability studies. I build models that capture subtle, often latent patterns in how people act, adapt, and decide over time.

Core strengths include probabilistic modeling, causal inference, time-series analysis, and predictive performance optimization in noisy behavioral data. My work sits at the intersection of statistical learning and behavioral science—designed to produce interpretable, actionable insights that support early detection, adaptive systems, and human-centered design.

This approach enables rigorous, theory-informed prediction of individual behavior—especially where precision and interpretability matter.

My work

  • 20+ peer-reviewed publications, the majority first-authored, many a team effort with great collaborators
  • 10+ open-source data sets including machine-readable meta-data and semi-automated data documentation
  • Data visualuzation and data storytelling expert
  • 3 statistical software libraries, including machine-learning classifiers and automated reporting (R statistics)
  • 1 platform for psychometric cognitive testing (Python to interface with Otree)

The languages I use most for

Top Langs Top Langs

Pinned Loading

  1. Cognitivemodels Cognitivemodels Public

    An R software package to write, train, tune, test, and compare machine-learning models of cognition

    R 26 4

  2. Psychometric-testing-platform-human-cognition-probabilistic-decisions Psychometric-testing-platform-human-cognition-probabilistic-decisions Public

    Production code for adaptive behavioral choice studies on human cognition in probabilistic situations (aka decisions under risk).

    Python

  3. Risk-preferences-and-risk-perception-affect-the-acceptance-of-digital-contact-tracing Risk-preferences-and-risk-perception-affect-the-acceptance-of-digital-contact-tracing Public

    A Bayesian feature-selection model identifying barriers to digital health device adoption during Covid-19. Proposal for strategies to increase uptake

    R

  4. The-influence-of-sample-size-on-preferences-from-experience The-influence-of-sample-size-on-preferences-from-experience Public

    A comparison between Bayesian and heuristic machine-learning models that learn probability information from experience under uncertainty.

    PostScript

  5. A-framework-for-building-cognitive-process-models A-framework-for-building-cognitive-process-models Public

    A conceptual framework for developing formal models of cognitive processes and a systematic review of 116 cognitive models

    R

  6. Naive-and-robust-class-conditional-independence-in-human-classification-learning Naive-and-robust-class-conditional-independence-in-human-classification-learning Public

    A new Bayesian model, DISC-LM, that adapts the naive Bayes assumption of class-conditional feature independence to efficiently learn new categories

    R

0