Philadelhpia, Machine Learning City Analytics

Machine learning

Our Machine Learning algorithm or exercise is based across different periods of time and different investment sizes. It takes into account various numeric and categorical data as well as spatial data and city features to perform and run a thorough machine learning moodel. The model aims to prove that while traditional intution and knowledge based investors have a general understanding of city with time and pricing, and if it changes doesnt specifically, machine learning mdoels can give clear,precise and objective answers and patterns of factors that shape pricing models across time and different price range.

Please Note : Hexbin images in CSR and Philadelhpia brief focus section, are generated as part of the regressions done in the machine learnig process, and hence the imporatnce of such factors can also be seen below in the charts.

Machine learning Patterns across time (correlations)

Here we see the correaltion matrix of importance factors across time. The first iamge is 2017-2018, followed buy 2018-2019, and the last is for this current year.

2017-2018

2018-2019

2019-2020

Machine learning Patterns across time

The following Charts shows importance factors as a result of machine learning for different time periods. A result is that this model is more clear, precise and objectively diffrentiates importance factors withindifferent periods of time, where as tradiotional investors with intutive and broad knowledge based understanding are likely to have just one general understanding of a city which doens change so clearly and objectively with time. Much learnig is thus very helpful and a powerful tool in driving the correct investment decesions.

Machine learning patterns across investment size

The following Charts shows importance factors as a result of machine learning for different investment size. A result is that this model is more clear, precise and objectively diffrentiates importance factors within price range where as tradiotional investors with intutive and broad knowledge based understanding are likely to have just one general understanding of a city irrespective of price range. Much learnig is thus very helpful and a powerful tool in driving the correct investment decesions.