lexijess / video_gaming_purchasing_pandas

Parsing out users of interest from purchasing dataset. Using python, pandas, Jupyter notebooks.

The source data for this project is video game purchasing histroy of a population. The project sorted out the various demographics, including which users purchased most freqeuently, which at the highest price points, etc. and other factors that may be of interest to game developers and marketers. Primary tools are python, pandas, and Jupyter notebooks.

Here are some trends visible in this dataset:

Those gamers in the 20-24 age range are the biggest spenders by almost triple the numbers of the next-closest category (the 15-19 age range). It's worth investigating if this is the result of young adults finally having their own credit cards/electronic payment accounts that teenagers do not have. Also, if this is related to young adults not being under parental supervision anymore.

The largest gender demographic represented is males, by a LOT. It's worth investigating if this is accurate to the IRL gender of the players or is a choice represented by women not wishing to be harrassed by presenting as female in an online forum.

While males are overepresented among this dataset, it's worth noting that female spend more per purchase and on average than males. "Other/Non-Disclosed" is the highest spender of all. It might be suggested to marketing personnel that pursuing the female/other demographic could be more profitable per player than catering to the male players, although, of course, the economies of scale in marketing still belong to males.