This dataset for Kenya combines preprocessed data from two data sources to create a rich source of information that can be used to develop a detailed understanding of poverty in the country. Content ---------- **Demographic & Health Surveys Preprocessed Data** The dataset contains preprocessed data from the DHS for Kenya. There are five main data files: 1. Household data 2. Household Member data 3. Births data 4. Cluster information 5. Geographic information (shapefile) The first three files contain all the features required for a complete calculation of the Multidimensional Poverty Index. The household member and births data both contain reference IDs that can be used to join them to a particular household in the household datafile. The cluster file contains information required to link each household to a particular cluster, which in turn can be associated with geographic location information. For detailed descriptions of the features available, refer to the [DHS Recode Manual][1]. For details on how the preprocessed data was obtained, refer to Part III of my submission for the Kiva Challenge https://www.kaggle.com/taniaj/kiva-crowdfunding-targeting-poverty-sub-nat . ---------- **Financial Inclusion Insights Survey Preprocessed Data** The dataset also contains preprocessed data from the FII Survey for Kenya. It contains features relevant for developing a financial deprivation indicator, such as whether the respondent has a formal bank account, whether they have formal savings and whether they have access to formal borrowing services. For detailed descriptions of the features available, refer to the [documentation][2]. For details on how the preprocessed data was obtained, refer to Part IV of my submission for the Kiva Challenge https://www.kaggle.com/taniaj/kiva-crowdfunding-adding-a-financial-dimension . ---------- **Other data** In addition to the main datafiles, there are a number of "_sjoin" files, which are intermediate steps in my kernel, where a spatial join was run locally and saved to be read back in due partly to sjoin not working on Kaggle servers, partly to save time. ---------- Terms of Use Please refer to the following pages for the terms of use: 1. [DHS Program Terms of Use][3] 2. [Intermedia Terms of Use][4] Acknowledgements The original data was provided by: 1. [The Demographic & Health Surveys Program][5], [USAID][6] 2. [The Financial Inclusion Insights Program][7], [Intermedia][8] Inspiration This dataset was added for use in the [Data Science for Good: Kiva Crowdfunding challenge][9] [1]: https://dhsprogram.com/publications/publication-dhsg4-dhs-questionnaires-and-manuals.cfm [2]: http://microdata.worldbank.org/index.php/catalog/2726/study-description [3]: https://dhsprogram.com/data/terms-of-use.cfm [4]: http://www.intermedia.org/terms-of-use/ [5]: https://dhsprogram.com/ [6]: https://www.usaid.gov/ [7]: http://finclusion.org/ [8]: http://www.intermedia.org/ [9]: https://www.kaggle.com/kiva/data-science-for-good-kiva-crowdfunding