Ryan C. Dallavia

Ryan C. Dallavia

Data Science & Machine Learning Enthusiast

Sitemap

A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.

Pages

Posts

Future Blog Post

less than 1 minute read

Published:

This post will show up by default. To disable scheduling of future posts, edit config.yml and set future: false.

Blog Post number 4

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

Blog Post number 3

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

Blog Post number 2

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

Blog Post number 1

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

portfolio

Resort Pricing Study – Data Wrangling

Our client is Big Mountain (a/k/a ‘the Client’, ‘the Company’), a Montana-based ski resort. Management at Big Mountain suspects it may not be maximizing its return on investment (ROI) relative to its peers in the market. Furthermore, Company insiders also lack a strong sense of which facilities matter most to visitors, particularly ones for which skiers are likely to pay more. To address these issues, we begin by wrangling the data provided by the client.

Resort Pricing Study – Data Pre-processing and Modelling

Here, we’ll start building machine learning models. Before diving into modelling, however, we’ll begin by considering how useful the mean value is as a predictor. We never want to go to stakeholders with a machine learning model only to have the CEO point out that it performs worse than just guessing the average! Our first model is always a baseline performance comparitor for any subsequent model. Next, we’ll build up the process of efficiently creating robust models to compare to our baseline forecast.

Resort Pricing Study – Modelling

In this notebook, we now take our model for ski resort ticket price and leverage it to gain some insights into what price Big Mountain’s facilities might actually support, as well as explore the sensitivity of price changes to various resort parameters. Note, this relies on the implicit assumption that all other resorts are largely setting prices based on how much people value certain facilities, and comparable prices are set correctly.

Is There Anything On? A movie recommendation system.

In this section, we present a low-rank, matrix version of a collaborative movie recommendation system. It outperformed one we constructed with hierarchical clustering by recommending more than two times as many watchable films to the user.

That’s Unusual! A Gaussian Anomaly Detection System

We implemented a Gaussian anomaly detection system to identify network servers that may be malfunctioning. Several non-obvious servers were detected. Had we used the naive model in which all servers are assumed to be ok, or an alternate model in which all servers warrant inspection, our sys admin would have wasted considerable time.

Who’s Who in our Customer Database? A study in data mining and clustering.

Customer segmentation models using both hierarchical and k-means clustering were constructed. These methods illustrate classic cases of unsupervised learning. Though unsupervised methods do not yield a prediction, the insight gleaned from a data mining exploration of this type can be used to guide, for example, the implementation of targeted marketing campaigns. The study is written in R and depends largely on the tidyverse and caret packages.

publications

talks

teaching

Teaching experience 1

Undergraduate course, University 1, Department, 2014

This is a description of a teaching experience. You can use markdown like any other post.

Teaching experience 2

Workshop, University 1, Department, 2015

This is a description of a teaching experience. You can use markdown like any other post.