The movie industry is arguably one of the biggest entertainment sectors. Nollywood, the Nigerian movie industry produces tons of movies for public consumption, but only a few make it to box-office or end up becoming blockbusters. The introduction of movie success prediction can play an important role in the industry not only to predict movie success but to help directors and producers make better decisions for the purpose of profit. This study proposes a movie prediction model that applies data mining techniques and machine learning algorithms to predict the success or failure of an upcoming movie (based on predefined parameters). The parameters needed for predicting the success or failure of a movie include dataset needed for the process of data mining such as the historical data of actors, actresses, writers, directors, marketing and production budget, audience, location, release date, and competing movies on same release date. This model also helps movie consumers to determine a blockbuster, hit, success rating and quality of upcoming movies before deciding on a movie ticket. The data mining techniques was applied to Internet Movie Database MetaData which was initially passed through cleaning and integration process.

Mining of big data brings out hidden knowledge that medium size and sample data cannot reveal. This research analyzed Nigeria Population Census data in order to bring forth knowledge that can aid Government in social-economic decision-making. Thus, k-means algorithm, which is an unsupervised learning technique, was implemented on MapReduce with the aim of discovering knowledge from Priority Table IX of Nigeria Census Data of 2005. MapReduce was used to aid k-means computational challenges such as Euclidean distance computation, minimum sum of square error (MSSE) computation and global objective computation effectively. The big data analytics revealed local government areas that need Government Intervention in terms of low cost housing and those local governments that need urban restructuring for good distribution of population. Further work can be done by implementing other data such as malaria data of children to reveal hidden pattern and knowledge.

No abstract