Alam, Md. AshrafulAlam, Md. Golam RabiulRahee, ArnobNafiz, Md. MontasirBhuiyan, Sania Azhmee2021-10-102021-10-1020212021-08ID 18101225ID 17109028ID 18101486http://hdl.handle.net/10361/15196Cataloged from PDF version of thesis.Includes bibliographical references (page 55-56).This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2021.Rainfall has always been important in context of Bangladesh as almost 43% of the population depends on agriculture for their livelihood. Global warming has been taking a toll on environment and rainfall patterns have been changing around the world. Almost half the population depends on rainfall for irrigating their lands and grow crops. If rainfall can be predicted precisely then people involved with agricultural sector will be benefited. In this research, we analyzed the rainfall statistics on the basis of Bangladesh Meteorological Department’s data of rainfall of last 66 years. With Mann-Kendall Trend Test with 5% level of significance we tested the trend of 6 divisional stations of Bangladesh. Later we utilized three regression models to predict rainfall on basis of data from 1948 to 2014. We have also implemented those 3 regression models on 6 regional station data to understand if there is any change in accuracy. Trend tests showed no significant change in rainfall patterns in last 30 years. We also broke down the data to understand the hydrological regions of Bangladesh and the rainfall by stations.56 pagesenBrac University theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission.Rainfall AnalysisMachine LearningRainfall in BangladeshRegressionK-Nearest NeighbourRandom ForestDecision TreeMachine LearningThesis