Skip to the content.

Home | Portfolio | GitHub | LinkedIn | Stack Overflow | Terms | E-mail

Portfolio

Here are some examples of how I have used Python and R to analyse business data. My focus centers around detecting patterns in data to reveal meaningful business insights - using a combination of data visualisation, machine learning, statistics, and time series techniques.

Data Visualisation

Analysing Hotel KPIs using plotly

The below is an illustration of a bubble chart created using plotly to visualise KPIs of two major hotel chains - specifically average daily rates, occupancy, and number of rooms. Interactive visualizations with dropdown menus were created using both Python Dash and R Shiny.

In the below examples, Dash was used to visualise Q4 2023 earnings data of Hilton Worldwide Holdings, and Shiny was used to visualise Q3 2023 earnings data of InterContinental Hotels Group.

Dash

hlt-639-dash

Shiny Web Apps

shiny-63822

Machine Learning and Time Series Analysis

Forecasting Hotel Revenue: Predicting ADR Fluctuations with ARIMA

Average daily rate represents the average rate per day paid by a staying customer at a hotel. This is an important metric for a hotel, as it represents the overall profitability of each customer. In this example, auto_arima is used in Python to forecast the average daily rate over time for a hotel chain.

hotel-adr-7

Handling Imbalanced Classification Data: Predicting Hotel Cancellations Using Support Vector Machines

When attempting to build a classification algorithm, one must often contend with the issue of an unbalanced dataset. An unbalanced dataset is one where there is an unequal sample size between classes, which induces significant bias into the predictions of the classifier in question. This example illustrates the use of a Support Vector Machine to classify hotel booking customers in terms of cancellation risk.

svm-2

Prophet and R: Forecasting Air Passenger Numbers

Prophet is a time series model that works well in forecasting time series with strong seasonality trends, with the ability to automatically detect changepoints in the series. Here is an illustration of the use of the Prophet library in R to forecast air passenger numbers, using flight data sourced from San Francisco Open Data.

prophet-640