Towards minimal algorithms for big data analytics with spreadsheets.

The motivation for our research is the need for a simple and accessible method to process large datasets available to the public. We aim to significantly lower the technological barrier, which currently prevents average users from analyzing big datasets available as CSV files. Spreadsheets are perfectly suited for this task, being the most popular and accessible data analysis tool. We present ideally balanced algorithms for specifying MapReduce computations of high number of range queries. With our algorithms, it will be possible to automatically perform analysis defined with a spreadsheet on data of size exceeding the dimensions of the spreadsheet grid by orders of magnitude.