Is Machine Learning ready to take over the world?

Pitfalls and considerations to be made while working with DS/ML features

  • In December 2019, Zillow started a house flipping hustle - “Offers”, allowing sellers to directly sell houses to Zillow thereby eliminating the lengthy bidding and closing process.
  • Zillow saw this as an opportunity to monetize and profit from the rich real-estate data at its disposal.
  • The “Offers” program was powered…

[ML Shot of the Day] Advantages of ReLU over Sigmoid Activation

Diving Deeper into Deep Learning — ReLU vs Sigmoid Activation function.

Ivan Aleksic — Unsplash
  • Over the last few years, Deep Neural Network architectures have played a pivotal role in solving some of the most complex machine learning problems.
  • Training a Deep neural network is not trivial and often involves billions of parameters trained over terabytes of data.
  • Building a robust trainable network is an…

[ML Shot of the Day]: Discretization of Continuous Attributes

Choosing the optimal splitting point for continuous attributes in Decision Trees

  • Decision Trees and its variants, Random Forests, XGBoost, CatBoost are popularly used in the Machine Learning world (including competitions).
  • Training a Decision Tree for a classification problem involves recursively splitting the data into smaller subsets until each node contains data belonging to a single class.
  • Different measures (Information Gain, Gini…

Dynamic Product Pricing: Python Implementation

Leverage Explore Exploit technique for determining the optimal product pricing for multiple products.

Mrunal Jadhav:
  • The COVID pandemic has accelerated the growth of E-commerce. The change in paradigm has forced businesses to undergo a digital transformation.
  • Businesses that relied heavily on foot traffic are setting up online stores in an effort to stay relevant and survive in the post-pandemic world.
  • Shopify’s increased market capitalization from…

Execute Algorithmic trades with higher confidence.

Leverage historical data for backtesting the MACD trading strategy for ANY ticker using Toucan and Python.

Photo by Jorge C on Unsplash
  • Moving Averages Convergence Divergence (MACD) is a widely used trading signal for detecting trend reversals.
  • By design, moving averages lag the underlying time series. As a result, the triggers from trading strategies purely based on Simple Moving Averages are often delayed resulting in missed opportunities or even losses.
  • MACD signal…

Multi-Label Classification

A survey of evaluation metrics for training a multi-label classifier in python

  • In a traditional classification problem formulation, classes are mutually exclusive. In other words, under the condition of mutual exclusivity, each training example can belong only to one class.
  • In such cases, the classification errors occur due to overlapping classes in the feature space.
  • However, often we encounter tasks where a…

Algorithmic Trading Using Python

Leverage historical data for backtesting the MA crossover trading strategy.

  • Imagine a computer program continuously monitoring markets and executing profitable trades on your behalf without any manual intervention. Sounds exciting but way riskier, doesn’t it?
  • The idea sounds risky because of the uncertainty associated with automated decision-making.
  • The goal of this blog post is to demystify algorithmic trading by piggybacking…

Autoselect Dream11 Fantasy Teams using Data Science

Leveraging Integer Linear Programming for selecting an optimal fantasy team on Dream11.

  • Sports have played a pivotal role in our society for ages. It has been an active medium for entertainment and a means for uniting people.
  • Sports have given us legends who are followed, loved, and worshipped across the globe.
  • Over the last few years, the emergence of fantasy sports platforms…

Product Pricing Using Reinforcement Learning.

Leveraging Explore Exploit strategy for determining the optimal price for a product.

  • The COVID-19 pandemic hit us hard in 2020 and forced us to seek safe havens by practically giving up on socializing. The pandemic also severely affected business and economic growth across industries and nations.
  • It also changed the way we have been conducting businesses until now. The lockdown and physical…

Demystifying Convex Functions

Testing the conditions for proving the convexity of mean squared error (MSE) function used in the context of Linear Regression.

  • The previous blog — The Curious Case of Convex Functions, focused on laying the foundation for testing the convexity of a function. It enumerates different ways to test/prove the convexity of a function.
  • In this article, we shall put that knowledge to use by proving the convexity of the Mean…

Pritish Jadhav

Data Science Engineer, Perpetua

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