Academia on Harshvardhan

Enterprise-Scale Machine Learning for Demand Forecasting

Sat, 18 Oct 2025 00:00:00 +0000

Our HP Inc. forecasting framework was featured in Foresight: The International Journal of Applied Forecasting (Issue 79, 2025) and recognized as a finalist at the International Institute of Forecasting’s Foresight Conference. 🔗 PDF

Print Demand Forecasting with Machine Learning at HP Inc.

Wed, 04 Jun 2025 00:00:00 +0000

HP Inc. replaced manual and statistical forecasting with a machine learning (LightGBM) model to improve demand prediction accuracy across 18,000+ print products. The model has been deployed enterprise-wide, with demonstrated business value and principles for scaling ML in large organizations. 🔗 PDF

From Data to Decisions: Enterprise Demand Forecasting with Machine Learning

Sat, 31 May 2025 00:00:00 +0000

My Ph.D. dissertation (University of Tennessee, 2025) develops a machine-learning-driven demand forecasting framework implemented at HP Inc., improving forecast accuracy by 34% and reducing inventory by 28%. 🔗 PDF

Why Academia?

Thu, 16 Nov 2023 03:00:00 +0000

Panel discussion on academic research as a career choice at my alma mater, IIM Indore

End-to-End Inventory Prediction and Contract Allocation for Guaranteed Delivery Advertising

Mon, 07 Aug 2023 16:00:00 +0000

End-to-End Inventory Prediction and Contract Allocation for Guaranteed Delivery Advertising

Wed, 07 Jun 2023 00:00:00 +0000

We proposed a novel end-to-end approach, the Neural Lagrangian Selling (NLS) model, to improve Guaranteed Delivery (GD) advertising by concurrently predicting ad impression inventory and optimizing contract allocation. The model incorporates a differentiable Lagrangian layer and a graph convolutional neural network to enable direct optimization of allocation regret and effective handling of various allocation targets and constraints. 🔗 PDF

How does GPT work? Understanding Generative AI Models

Wed, 26 Apr 2023 00:00:00 +0000

Curious about ChatGPT, the AI chatbot that’s making waves? Dive into this article to learn how it generates human-like responses and its many applications. Get insights into both its strengths and limitations, while understanding why it’s essential to approach its responses with a critical eye.

CK Cafe: Using Association Rules to Find Basket of Goods

Mon, 21 Nov 2022 11:30:00 +0000

In this lab session, I share how to use apriori algorithm for association mining. The goal is to find useful causal and association rules which can help in designing promotions for the company. Plus, you get to see what’s served at an Indian cafe.

Next — Today I learnt About R

Sat, 18 Jun 2022 00:00:00 +0000

What is Next?

A short and sweet curated collection of R-related works. Five stories. Four packages. Three jargons. Two tweets. One Meme.

You can subscribe by providing your details here. Promise, no spams.

If you are unsure, here are some editions that my readers loved.

Personal Websites for Academics

Thu, 31 Mar 2022 13:00:00 +0000

Kick-off Workshop for University of Tennessee’s INFORMS Chapter