Creation and differentiation of regions are some of the basic tasks in geographic analysis. Regionalisation attempts to create a generalised representation of the processes which is taking place at the level of the amalgamated geographic units. To this end, this study examined the combined use of demographic, economic and poverty characteristics of States across Nigeria to create regions relevant for economic and development planning. The study utilised dependency ratios derived from gridded age structure data, Gross domestic product (GDP), poverty index. K-Means and Max-p algorithm were used for identification of regions. Correlation analysis showed that Youth dependency and total dependency have a strong statistically significant positive relationship (r=0.998, p<0.01) indicating that dependency in the country is driven by youth. The best K-Mean clustering implementation without considering contiguity identified 12 regions with a ratio of between and total sum of squares (RBTSS) of 0.789. The Max-p algorithm was tested with population constrain, the best result identified 9 regions with RBTSS of 0.611 constrained by a minimum population of 8% and implemented with the greedy local search algorithm, this was the same for the simulated annealing approach (SA). With high dissimilarity still common across a handful of the regions identified, a further test was carried out using a minimum bound of 3 States and the SA local search approach. The best result identified 11 contiguous regions with only one region having a relatively high within region dissimilarity and a RBTSS of 0.626. The results confirmed that there are more than 6 regions as currently defined for the country. The analyses showcased an example of knowledge discovery from a spatial dataset which could support regional development planning. From the results, there is a clear need for re-examination of current regions and designing of better-defined regions to ensure that development is guided by evidence.