Forecasting of Literacy Rate Using Statistical and Data Mining Methods

Chhattisgarh state ranks 16 position in terms of population in India but it ranks 27 in terms of literacy rate. This backwardness is due to more tribal areas in this state. Since literacy is the basis for human development which in turn affects country’s economic growth, it becomes important to improve the proportion of literates. Forecasting of literacy rate will help government & policy makers to make plans for improving the literacy rate. Number of literates in an area depends on various features like population of the area, density, type of area-rural or urban, age composition etc. In this research paper, total Population, male and female population is projected using a statistical method logistic curve method. Using these projected populations, literacy rate is forecasted using a data mining method multiple regressions. Using this combinational method, we forecast that the total population of Chhattisgarh in 2021 will be around 3 crores and the literacy rate will reach 89%. The accuracy of our combinational method is 92.69% which is much better than the results obtained from one of the proposed method Global Age-specific Literacy Projections Model (GALP) for forecasting of literate and illiterate population.