Pallavi Kulkarni

Logistic Regression Learning Model for Handling Concept Drift with Unbalanced Data in Credit Card Fraud Detection System

Credit card is the well-accepted manner of remission in financial field. With the rising number of users across the globe, risks on usage of credit card have also been increased, where there is danger of stealing credit card details and committing frauds. Traditionally, machine learning area has been developing algorithms that have certain assumptions on underlying distribution of data, such as data should have predetermined and fixed distribution. Real-word situations are different than this constrained model; rather applications often face problems such as unbalanced data distribution. Additionally, data picked from non-stationary environments are also frequent that results in the sudden drifts in the concepts. These issues have been separately addressed by the researchers. This paper aims to propose a universal framework using logistic regression model that intelligently tackles issues in the incremental learning for the assessment of credit risks.

Prediction of Student's Performance based on Incremental Learning

It is necessary to use Student dataset in order to analyze students performance for future improvements in study methods and overall curricular. Incremental learning methods are becoming popular nowadays since amount of data and information is rising day by day. There is need to update classifier in order to scale up learning to manage more training data. Incremental learning technique is a way in which data is processed in chunks and the results are merged so as to possess less memory. For this reason, in this paper, four classifiers that can run incrementally: the Naive Bayes, KStar, IBK and Nearest neighbor (KNN) have been compared. It is observed that nearest neighbor algorithm gives better accuracy compared to others if applied on Student Evaluation dataset which has been used.

Rainfall Statistics Change in West Bengal (India) from Period 1901-2000

The study aims to investigate rainfall trends in West Bengal, India. The paper deals with monthly, seasonal and annual general rainfall trends. The study is carried out to understanding the underlying feature for the purpose of forecasting and in identifying the changes and impact that are very crucial for an agro-based economy like the one of West Bengal, India. Here we studied using monthly data series of last 100 years (1901-2000). The methodology has been adapts various statistical approaches in order to detect the possible precipitation changes in annual, monthly and seasonal basis; including both the non-parametric tests for monotonies trend (Mann-Kendall test, Sequential version of Mann-Kendall test and Sen’s estimator of slope). Maximum of the districts showed an increasing trend in annual rainfall, but only one district (South 24 Pargana), this trend was statistically significant. In case of Monsoon months (June to September) maximum number of districts shows the increasing trend but it is not statistically significant. Only three districts (Midnapur west, North 24-Parganas and South 24-Parganas) of them are statistically significant. The majority of districts show very slight change in rainfall in non-monsoon months.

An AIMD Distributed Control Law for Load Balancing in Content Delivery Networks

Content Delivery Networks (CDN) is the best for overcoming the inherited problems face by internet in modern days. The major idea at the basis of this technology is the delivery at edge points of the network, in proximity to the request areas, to advance the user’s perceived performance while off-putting the overheads. Literature shows that in Content Delivery Network how this demanding problem of defining and implementing an effective law for load balancing is model. But this system has some drawback, like even if the queue length of server is low they redirect loads to another server to only balance the overall load. Due to this request processing overhead and delay increases. Algorithm model in paper can help to reduce this delay by putting one equilibrium point to request queue. In CDN, the source adjusts its rate using a modified Additive Increase and Multiplicative Decrease (AIMD) algorithm. AIMD has been demonstrated to be sufficient and essential of efficiency and fairness under certain general conditions.