The vast amounts of economic data currently being generated and collected calls for the application of new methodologies in order to make sense of them. It is for this reason that we have undertaken the analysis of some of data collected on the informal sector of the Nigerian economy using data mining and machine learning techniques. This is different from the traditional bare statistical methods hitherto being used in such analysis. In this work, we used data gathered by the National Salaries,

more »

... Incomes and Wages Commission (NSIWC) on the informal sector of the Nigerian economy between the year 2014 and 2016. These data were subjected to analysis using WEKA data mining/machine learning tools and the Random Forest ensemble algorithm. The results show that the modal population age group of Nigerians working in the informal sector is in the age bracket of 30-44 years. Similarly, it was discovered that wholesale business is the dominant activity in the informal sector and women's participation in informal sector business is still low compared to their male counterparts. This study shows the relevance or implication of utilizing data mining methodologies over the conventional statistical analysis of data. The data we collect these days in such huge amounts could be useful if we had the ability to organize and transform them in such a way that they provide useful insights into our everyday activities and also provide us with useful guides and options for our future actions. While technological advances have solved the problems of storage and organization of data on a large scale, gaps remain to be filled with respect to the transformation of the data and the extraction of useful information from them. These gaps are currently being filled by Data Mining and Machine Learning methodologies.