Crime detection is one of the most important research applications in machine learning. Identifying and reducing crime rates is crucial to developing a healthy society. Big Data techniques are applied to collect and analyse data: determine the required features and prime attributes that cause the emergence of crime hotspots. The traditional crime detection and machine learning‐based algorithms lack the ability to generate key prime attributes from the crime dataset, hence most often fail to predict crime patterns successfully. This paper is aimed at extracting the prime attributes such as time zones, crime probability, and crime hotspots and performing vulnerability analysis to increase the accuracy of the subject machine learning algorithm. We implemented our proposed methodology using two standard datasets. Results show that the proposed feature generation method increased the performance of machine learning models. The highest accuracy of 97.5% was obtained when the proposed methodology was applied to the Naïve Bayes algorithm while analysing the San Francisco dataset.

Business locations is most important factor to consider before starting a business because the best location attracts more number of people. With the help of web search engines, the customers can search the nearest business location before visiting the business. For example, if a customer need to buy some jewel, he makes use of search engines to find the nearest jewellery shop. If some entrepreneur wants to start a new jewellery shop, he needs to find a best area where there is no jewellery shop nearby and there are more customers in need of jewel. In this paper, we propose an algorithm to find the best place to start a business where there is high demand and no (or very few supply). We measure the quality of recommendation in terms of average service time, customer-business ratio of our new algorithm by implementing in benchmark datasets and the results prove that our algorithm is more efficient than the existing kNN algorithm.

With the exponential increase in a number of web pages daily, it makes it very difficult for a search engine to list relevant web pages. In this paper, we propose a machine learning-based classification model that can learn the best features in each web page and helps in search engine listing. The existing methods for listing have lots of drawbacks like interfacing the normal operations of the website and crawling lots of useless information. Our proposed algorithm provides an optimal classification for websites which has a large number of web pages such as Wikipedia by just considering core information like link text, side information, and header text. We implemented our algorithm with standard benchmark datasets, and the results show that our algorithm outperforms the existing algorithms.