Analysts and investors use data on market activity, such as historical returns, stock pricesopen, high, low, close, and volume of trades to chart patterns in securities movement. With technical analysis investors can get mixed signals. For stock market predictions using technical analysis, various Machine Learning algorithms are available. A novel algorithm formulated on History Bits is hatched for deriving beneficial facts from the massive established dataset which is stored on a private blockchain for the quick retrieval and avoid data manipulation. The proposed algorithm predicts the trading call out of five different calls-strong buy, strong sell, buy, sell, and hold. For the implementation and testing of the History Bits based algorithm, 75 technical parameters are computed using stock trading data (open, high, low, close prices, and volume), prioritised using ensemblebased rank search strategy acting as an input for the proposed algorithm. For the experimentation, transformed NIFTY 50 dataset was used over the time frame of 20 years. The performance of proposed History Bits model is compared with Decision Tree, Naïve Bayes, Random Forest, Support Vector Machine and Multilayer Perceptron Artificial Neural Network, algorithms. History Bits algorithm outperforms machine learning algorithms in terms of prediction accuracy.

India is a developing country. Increase in personal vehicles comes with the development of a country parallely. This has led to rise in congestion in large cities. So, we need a better traffic management system. The purpose of this project is to create a traffic system which is adaptive to the present traffic scenario in a lane. Usually, we have fixed average waiting time for all lanes. This project suggests to change the average waiting time by monitoring the number of vehicles in a lane. The data will be sent to central system through internet, which will decide the timing for signal according to the dumped program. This project also, suggests implementing congestion lights at previous intersections, so that drivers can change lanes at the situation of congestion. The system is useful in emergencies and it also, helps in reducing pollution and traffic congestion.

Data mining is very effective technique for extracting useful information from large amount of structured dataset. Number of algorithms are available that can mine the useful and relevant information. Use of particular data mining algorithm has great impact on the results obtained. An innovative classification algorithm based on History Bits is developed for extracting useful and relevant information from large structured dataset. For implementation and testing of the History Bits based algorithm we have designed a structured criminal dataset. This algorithm analyses criminal information in lesser time and reduces the constraints of manual investigation process.

No abstract

Sentiment analysis can be a useful tool in predicting stock market trends, as it allows us to gauge the overall sentiment towards a particular stock or company. When combined with news stored in a blockchain, sentiment analysis can provide a more accurate and trustworthy representation of the market. The aim of this paper is to study the spatial news and external events which disrupt the stock market movement as well as news analytics techniques to understand the impact of news by spatial sentiments on stock market movement. For the prediction of stock market trading decisions, a novel ensemble technique consisting of spatial federation of deep learning algorithms, machine learning algorithms and dictionary based approach is proposed to maintain privacy and geographic diversity. These learning techniques are federated into five groups and these groups are ranked as per the prediction accuracy of these models. A bit 1 or 0 is assigned for each federation thus creating a 5 bit pattern which can be used to predict stock market trading decision as strong buy, buy, hold, strong sell, sell.