Alex Liebscher

About

I am a third-year undergraduate at the University of California: San Diego. I am majoring in Cognitive Science and minoring in Mathematics because I want to develop machine learning language models that are ethical and human-centered. I enjoy the challenges of trying to model human comprehension of language, a dynamical phenomenom rife with uncertainty. Moreover, for me, it's incredibly important that the intelligent technologies that we're becoming increasingly reliant on are sensitive to the needs of the user.


Contact

The best way to reach me is at x@gmail.com where x = alexliebscher0


Experience

San Jose, CA | June 2018 - September 2018

I was a data science intern for TextRecruit during the summer of 2018. I discovered usage and performance insights from the company's large collections of customer and user data. I focused my time on the 40+ million messages the company had transmitted through their platform. I built a sentiment analysis model which improved F1 scores over 1.7x compared to other out-of-the-box solutions. I wished to model the flow of text message conversations with the company's artificial intelligence chatbot to determine retention and confusion rates, along with drop off points. I engineered two classification models to tag inbound user text messages and outbound chatbot messages as one of 30 or 34 classes, respectively. These were applied to conversations to generalize the structure and present insights on weaknesses in the platform's NLP capabilities. I also provided KPIs about chatbot usage, and customer activity and growth, which helped company leadership validate business decisions.

Tools: Python (Keras, Tensorflow, nltk, spaCy.io), Java, Github & git, Jira & Atlassian


Peak Landscape, Inc.

Truckee, CA | July 2017 - August 2017

Maintained and upkept the yards and gardens of large residential and commercial properties. Developed a keen sense of detail, an indefatigable work ethic, and the character to place myself in uncomfortable situations and drive myself toward the company’s idea of success.

Education

La Jolla, CA | September 2016 - June 2020


Favorite Courses

Cognitive Science Computer Science and Math Electives
Supervised Machine Learning Probability Race, Gender, and Artificial Intelligence
Unsupervised Machine Learning Mathematical Statistics Public Rhetoric & Practical Communication
Computational Models of Cognition Vector & Multivariable Calculus Hip-Hop
Language Data Analysis and Inference
Cognitive Consequences of Technology Intro to CompSci: Java I & II
Neuroanatomy and Physiology Linear Algebra
Sensation and Perception Differential Equations
Research Methods and Statistical Analysis

Projects

Functional Role of Metaphor Framing in Cancer-related Crowdfunding Projects

Fall 2018 - Present


Are there real-world observable consequences of using metaphors to discuss cancer patient behavior and outcome? We are analyzing a corpus of crowdfunding campaigns related to cancer to determine the functional role of metaphor framing when people discuss their hardships with cancer.

Tools: Python (pandas), R, Github & git

A Revised Empirical Comparison of Supervised Learning Algorithms

Fall 2018

Read the paper or browse the code


For any classification problem, choosing a proper classifier and its parameters is critical for success. This paper is my attempt at pushing for methodical supervised machine learning. I evaluate the performance of seven classification algorithms across four data sets. For thoroughness, each classifier was tested over three independent trials, where each trial was subject to three partitions of the data. For each partition of the data, cross validation was performed. For each CV fold, an optimal set of hyper-parameters was found for the classifier using Bayesian Search. Contrary to traditional grid search, this method improves performance, takes advantage of the underlying parameter space with specific priors, and reduces redundant and insignificant searches. Performance overall proved that Random Forests, Gradient Boosted Trees, and RBF-SVM achieve the highest results. K-Nearest Neighbors may also be a viable solution but should be treated with care and precision.

Tools: Python (pandas, numpy, scikit-learn, xgboost, scikit-optimize, multiprocessing), Github & git

Simile Generation with Gaussian Mixture Models

Fall 2018

Watch my presentation or browse the code


For this course project, I was interested in building a model with the ability to "fill in the blanks" when presented with a statement such as "Her hair is as red as ____". For this, I created my own dataset and annotated certain components of each simile. These similes were embedded in a vector space with Word2Vec. I then went through a model selection process in which I tried to minimize the model complexity and data complexity, while maximizing the prediction output entropy. I reduced the word embedding space (for better generalization), tuned the number of components of the Gaussian Mixture Model (representing the number of semantic topic groups), decreased the probability of the model fitting randomness, and maximized the entropy of the bin counts of predicted GMM components (to prevent most similes from being clustered under one component). Given partial data (an incomplete simile), the model permutates over all possible combinations of latent components and vocabulary, searching for the maximum log probability solution. This solution is the "blank" in which to fill the simile. Some results are intriguing, creative, and plausible, whereas others are (fun sounding) gibberish.

Tools: Python (spaCy.io, Word2Vec, scikit-learn, seaborn/matplotlib), Github & git

Music Listening Behavior Analysis

December 2017 - Present

Jupyter Notebook


I love talking about music: learning about new artists and songs, discussing albums, and debating the lyrics of music. I might argue that my taste in music defines my friend-circle to some degree. When I meet new people, often times one of the first questions I'll ask is, "So what kind of music do you listen to?" or "Who are your top three artists right now?" Music can tell you a lot about a person, and I take this to heart. Hence, this project is an attempt to understand me a little better.


This project exlores my music listening behavior, including how much music I listen to, listening timeframes, the diversity of my music, and out of all the music I listen to (which averages about 5 hours per day!), what music I actually enjoy.