About Me.

Hey there!

I am Akash Singh, a second year data science student at KTH, Sweden.

I am looking for full time machine learning/data science roles starting this July.

Please get in touch if you have an opportunity for me.



  • Doing master thesis with the Machine Learning Group at Ericsson Research, Stockholm. Thesis is on “Deep learning for Anomaly Detection on Temporal Data”.

  • Part of another project on anomaly detection and predictive maintenance using sensor data from manufacturing production line.

  • Using LSTMs, autoencoder, Gaussian Process and Bayesian optimization.


Lead Engineer

  • Part of 99acres search and analytics team. 99acres is the leading real estate search portal in India and part of the Info Edge group.
  • Built a dynamic search ranking framework to rank search results by balancing listing relevance, agent lead demand and paid subscriptions.

  • Developed the search backend using Apache Solr, and named entity recogniton.

  • Executed machine learning projects including click-through rate prediction, and spam classification.

  • Worked with Java, R, mongodb, Apache Solr.


Applications Engineer

* Part of [Oracle FUSION Middleware](https://www.oracle.com/middleware/index.html) development team. Oracle Fusion is Oracle's cloud based suite of enterprise solutions. * Worked on Fusion Product Information Management tool which is part of from the Fusion Supply Chain Management family. PIM's customers included Boeing, Posco, GE.


Breaking Captchas

  • Build a CNN based deep learning model to learn and break captchas.

  • The project was done as part of deep learning course at KTH with Tharidu and Dominik.

  • Trained the model on a dataset of 200,000 captchas on Nvidia Tesla K80 GPU an AWS EC2 instance.

  • Tensorflow was used as the deep learning library.

  • The model achieved an accuracy of ~98%.


Collaborative Deep Learning

  • Deep learning based Collaborative Filtering for Recommendation Systems.

  • The project is based on the paper.

  • MXNet was used as the deep learning library.

  • Reproduced results of the CDL paper and compared it to other approaches.


Dutch Asylum Seeker

* **[Visualizing Asylum Requests to Netherlands from 2007-2015](http://www.akash13singh.me/dutch-asylum-seeker/)**. * The [project](https://github.com/heytitle/dutch-asylum-seeker) was done as part of Visualization course at TU/e, with Pat. * Developed an interactive D3.js website (live [website](http://www.akash13singh.me/dutch-asylum-seeker/)). * Intuitive & iteractive graphs and maps to understand asylum request data.


Triest: TRIangle Estimation from STreams

* **Counting Global and Local Triangles in Streaming Graphs**. * The [project](https://github.com/akash13singh/Triest/) was done as part of Data Mining course at KTH. * Implementation of [paper](http://www.kdd.org/kdd2016/subtopic/view/triest-counting-local-and-global-triangles-in-fully-dynamic-streams-with-fi). * Triangle count is commonly used in network analysis, random graph models, and real world applications like link-recommendation, spam detection etc.


Opinion Mining & Sentiment Analysis

* **Opinion Mining & Sentiment Analysis of Laptop Reviews**. * The project was done as part of Web IR course at TU/e. * A system for opinion mining, sentiment analysis, searching and clustering of amazon laptop reviews. * I was mainly responsible for building the search engine and clustering system for the project.