Quarterly call word sentiment overlaid with stock prices
Quarterly call word sentiment overlaid with stock prices


The objective here is to analyse the quarterly earnings conference call transcripts, with the help of NLP, to identify the new themes, opportunities and risks that company management is sharing with the investors.

The toolkit used for analysis includes Spacy for natural language processing, Scikit-learn’s TF-IDF to identify topics of higher importance during call, as well McDonald’s sentiment word list to identify the sentiments during the call.

In this post I will describe what has been achieved in words without code. I have realised that writing technical code on medium can get a bit dry to read so I’ll just be discussing the concepts, tools and usage of tools here. To see the code with detailed description of flow and function calls, I have created a well documented Jupyter-Notebook on Github and one should be able to follow it step by step. …

Image for post
Image for post
Photo by Fotis Fotopoulos on Unsplash

Available with pre-configured settings for logging, configuration settings, URL parameter validation

Let’s assume after lots of hard work you have your machine learning model running the way it should. This model could be one which responds to a user’s request to classify a tweet sentiment or identify objects in an image or recommend a product or some other algorithm unique to your needs. You would now like to quickly deploy this model. The article below is an explanation of the template that I have created to get you up and running quickly.

Flask micro service is an easy way to deploy applications. However, one soon realises that you do not want to create a large monolithic single file program. The program should be modular to support future enhancements and it should be configurable with help of a configuration file. These configuration parameters are not only for Flask but also for your business application program (remember the tweet classification application you have created). Ideally the server should appropriately log everything. Most applications also need to connect to a database and finally, the inbound request parameters needs to be validated before invoking the model api (or return error). …

Image for post
Image for post
Photo by Vlad Shapochnikov on Unsplash

…and my thoughts behind my actions

In this day and age everyone is talking about climate change and the governments of the world not doing. While we are waiting for the governments to bring about the changes in legislation can we do something? I read a lot of internet and found quite a few things that we can implement in our day to day life to contribute to this cause.

Image for post
Image for post
Photo by Charles 🇵🇭 on Unsplash

In this article, I will describe how to create your personal email secretary.

This email secretary is an email application that reads your email using Gmail API, reads out your email using Google Text-to-Speech API and ‘playsound’ API, it hears your response using ‘pyaudio’ API converting the audio response into text using Google Speech-To-Text API and finally sends out the response again using Gmail API.

To see this email assistant in action, see the video

I am sure you are curious to see how it was created and what all steps are required. So let’s dive right into it. …


Anirudh Lohia

A banker by profession, a technology enthusiast in evenings and passionate about environmental issues

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store