This document discusses using Bayesian inference and causality analysis to estimate the causal effect of attributes on house prices using the Boston housing dataset. It introduces the Boston housing dataset which contains various attributes of houses and towns in the Boston area like crime rates, proportions of various land types, nitric oxide concentrations, room counts, ages of homes and more. It then discusses using Bayesian linear regression and the DoWhy library to perform a causal analysis on this dataset to determine the causal relationships between attributes and median home prices. The document concludes by thanking the reader and mentioning the team that worked on this analysis.