Client Name

Quantree Private Limited

Faculty Advisor

Mr. Vishal

SBS Thought Leadership Areas

Investment Decision Making

SBS Thought Leadership Area Justification

This project improves investment decision-making by replacing subjective judgement with a structured, data-driven approach to agricultural commodity futures markets. Instead of relying on intuition or looking at price movements in isolation, the study develops a framework that analyses different variables, including macroeconomic conditions, energy costs, exchange rates, climate indicators, and market positioning. By examining both correlations and time-lagged relationships, the research identifies how these factors influence future commodity prices.

Aligned SDGs

GOAL 9: Industry, Innovation and Infrastructure

Aligned SDGs Justification

At its core, the project is built on innovation. It leverages quantitative research, statistical analysis, machine learning concepts, and algorithmic trading techniques to solve complex investment problems. By integrating economic, environmental, and market data into a unified decision-making framework, the project showcases how modern financial technology can improve market infrastructure and create more sophisticated tools for investment analysis and risk management.

NDA

No

Abstract

Agricultural commodity markets are among the most complex and consequential financial markets in the world, sitting at the intersection of weather, geopolitics, macroeconomic forces, and human food security. This project set out to understand what actually drives price movements in these markets and whether those drivers can be systematically exploited to make better investment decisions.

Using wheat as the primary case study and extending the analysis across a broad universe of agricultural futures, the research assembled a comprehensive dataset spanning over two decades of daily observations. Variables were drawn from multiple domains including energy prices, fertiliser costs, exchange rates, climate indices, and market positioning data, all merged into a unified analytical framework. The exploratory analysis revealed that agricultural commodity prices are shaped by a richer and more interconnected set of forces than price charts alone can capture, with urea fertiliser costs, crude oil prices, and the US dollar emerging as the most powerful explanatory variables.

Three systematic trading models were then developed and rigorously tested. The process uncovered something that many practitioners intuitively sense but rarely quantify: these markets do not behave consistently over time. They trend in some conditions and mean revert in others, and the difference between a profitable strategy and a losing one often comes down to correctly identifying which regime is in play. Each model iteration brought sharper insight into that problem, progressively reducing drawdowns and improving risk adjusted performance by filtering out the noise.

The broader ambition of the project was to demonstrate that disciplined quantitative research, grounded in economic reasoning and tested honestly against real data, can meaningfully improve the quality of investment decisions in one of the oldest and most important asset classes in global finance.

Document Type

Restricted Access

Document Name for Citation

Experiential Learning Project

Download

Share

COinS