This storage contains files described in a PhD thesis titled 'Personalisation of a DHBCI for midlife women in the UK', by Hana Sediva, dated 24/5/2024. The files correspond to Chapter 8 titled 'Predicting Health Behaviours in UK-Residing Midlife Women Using Machine Learning with Ecological Momentary Assessment and Fitness Tracker Data: An Exploratory Study'. The storage contains: 1) Intervention dataset generated programatically in R and used in all ML analysis (ThesisMLDataFile.csv) 2) Time-varying predictors used to access the dataset in Python (dfPredictors.csv) 3) Weighted spearman correlation file generated in R (csv) 4) Python code for feature selection created in Jupyter Notebook (.ipynb) 5) Python code and results for feature selected in PDF (.pdf) 6) R code for feature selection created in R studio as R Markdown (.rmd) 7) R code for feature selection in PDF (.pdf)