I'm Umanga Bista from Kathmandu, Nepal . I am interested in scalable Machine learning, data streaming algorithms and distributed systems.

I'm Research Assistant @LogPoint Lalitpur, Nepal, a SIEM product. I primarily work on building statsical analytics in streaming environment and on building scalable (and real time) architecture (using lambda architecture design principles)

I'm also Student @Coursera, Edx.

Research Interests

  • Streaming algorithms (at scale)
  • Scalable Machine Learning

Skills

  • Programming: Scala, Python, Java
  • Distributed tools: Mesos, HDFS, Kafka, Zookeeper, Akka, Flume
  • Analytics tools: Spark, R, Scipy + Ipython eco.
  • Others: Intellij Idea, $\LaTeX$, Git, Sublime, , MarkDown, Jekyll, Vim

Past

I was a computer engineering student at Institute of Engineering, Central Campus Pulchowk, Lalitpur, Nepal [2009-2013].

Previously, I have worked on financial data representation and mining using XBRL for annual financial statements collected by Office of Company Registrar, Nepal [2012 oct to 2013 sept].

Conference Papers
  1. Joshi, B., Bista, U., & Ghimire, M. (2014). Intelligent Clustering Scheme for Log Data Streams. In A. Gelbukh (Ed.), Computational Linguistics and Intelligent Text Processing (Vol. 8404, pp. 454–465). Springer Berlin Heidelberg. doi:10.1007/978-3-642-54903-8_38
Techical Reports
  1. Bista, U., Basnet, A., Shrestha, A., & Pant, S. (2013). XBRL Implementation for Financial Reporting to the Office of Company Registrar. Pulchowk, Lalitpur, Nepal: Institute of Engineering, Central Campus Pulchowk, Tribhuvan University. Retrieved from https://www.dropbox.com/s/04kyzyx5hsemsth/major%20report%20XBRL%20Implementation.pdf

umb, powered by jekyll, bootstrap, gh-pages