My fascination in DataScience is derived from, when I see product recommendations in shopping websites,customized advertisement in social media, accurate TV shows and movierecommendation in streaming websites. I am astonished by the huge amount ofdata and what the algorithms could achieve in helping individuals ororganizations to make better decisions and elevating the existing processes.Apart from these data science has been extensively used in sports, healthcare,elections, marketing etc. The use of data science is destined to become evenmore extensive, wide ranging and far reaching. I feel enthusiastic and excitedabout the use of computer science and statistics to predict and arrive at betterdecisions and its impact on society. I want to contribute to this evolution andhave an influence, thus I would like to pursue a Master degree in Data Science.My father’s officehad a computer and I used to go there to mostly play games. During my highschool years, my dad suggested me to learn something instead of playing games.
I started with HTML and thus my journey in Computer Science began. The logicand creativity required to be a good programmer intrigued me, and I discoveredI had a passion for it. I secured a merit seat in Sir M Visvesvaraya Instituteof Technology majoring in Computer Science & Engineering and it has broughtme to where I am today. During my undergraduate studies I explored manyfascinating subjects, especially programming in C & C++, Data Structures, Designand Analysis of Algorithms, Graph Theory, Database Management Systems. Imastered C and SQL, along with my other undergraduate courses.
As Graph Theorywas one of the subjects that intrigued me, I tried creating a social networkgraph of students in my college to detect clusters. Even though it did notproduce desired results I learnt a lot from the project and was appreciated formy efforts by my professor.During my thirdyear at college I had the chance to build an interactive database system forthe college medical centre. The college organizes an annual blood drive. Withthe help and guidance of the faculty members of the Computer Sciencedepartment, we built an interactive database whose function was to keep trackof valid donors among thousands of students and organize the donor data basedon availability and proximity of the donor. It was possible to keep track ofpotential donors and contact them through an SMS system, without beinginvasive.
This experience provided an insight into how working with data in aneffective manner is necessary to gain the right answers to solve differentproblems.My first majorproject was done in the final semester of undergraduate study. We were a teamof three and our project was “Libra – Lightweight data skew mitigation inMapReduce”. The project was based on a research paper which suggested an efficientand lightweight algorithm to prevent data skew in distributed computing modelslike MapReduce by sampling of 20% of dataset to determine the type and skewnessof the data. The algorithm has negligible overhead and can speed up theexecution of some popular applications by up to a factor of 4.1.
We implementedthe algorithm using Java, Hadoop-MapReduce.