I am aresearcher at the University of Oslo, specializing in artificial intelligence applications for mental health, particularly, adolescent suicide attempts and violent extremism. My focus is on developing machine learning algorithms tailored to predict rare outcomes, i.e., modeling outcomes undersevere class imbalance. My research extends to enhancing machine learning transparency, particularly in conceptualizing and stabilizing feature importance. Additionally, I am also interested in advancing statistical methods in missing data imputation and to this end, I have developed a machine learning imputation algorithm for single and multiple imputation that outperforms common statistical procedures. My former interest in statistics centered on reproducible research, where I contributed to procedures for documenting, reporting, and defensive coding of statistical analyses in Stata and R.

I use GitHub mostly for software development inR,Stata, andPython. Below is a list offree software I've developed. Almost all of my Python packages are developedd for the industry and thus are not publically available. Feel free to contact me for feedback or ideas regarding my algorithms and packages. For updates on my software, follow me on Twitter:@haghish.

I have written multiple R packages for artificial intelligence as well as general statistical use. My recent software particularly focuse on machine learning, for example, missing data imputation with machine learning, developing automated stacked ensemble machine learning models for classification under severe class imbalance, toolkits for comparing different properties of machine learning models, as well as innovative procedures for assessing model transparency and classification fairness.

PinnedLoading

1. HMDAHMDAPublic

   Holistic Multimodel Domain Analysis: A New Paradigm for Robust, Transparent, And Reliable Exploratory Machine Learning that Considers Cross-Model Variability in Feature Importance Assessment

   R 1

2. shapleyshapleyPublic

   Weighted Shapley Values and Weighted Confidence Intervals for Multiple Machine Learning Models and Stacked Ensembles

   R 16 1

3. mlimmlimPublic

   mlim: single and multiple imputation with automated machine learning

   R 31 1

4. rcallrcallPublic

   Seamless interactive R in Stata. rcall allows communicating data sets, matrices, variables, and scalars between Stata and R conveniently

   Stata 94 31

5. markdocmarkdocPublic

   A literate programming package for Stata which develops dynamic documents, slides, and help files in various formats

   Stata 92 32

6. githubgithubPublic

   a module for building, searching, installing, managing, and mining Stata packages from GitHub

   Stata 106 39