Ramasuri Narayanam  Ramasuri Narayanam photo         

contact information

Research Scientist
IBM Research, India
  +91dash80dash670dash43817

links



Tutorial: "AI Techniques for Price Prediction of Commodities"

Authors:Ramasuri Narayanam, Rohith Vallam, Ritwik Chaudhuri, Manish Kataria, Gyana R. Parija, Fatemeh Jahedpari
Email: framasurn,rovallam,charitwi,mkataria,gyana.parijag@in.ibm.com, F.Jahedpari@bath.ac.uk

 

Abstract:

In this tutorial, we wish to cover the foundational, methodological, and system development aspects of Price Prediction of certain raw materials in spot markets (such as Ethylene, Hydrocorbons and Methyl Methacrylate) that are volatile as well as not traded through online Exchanges. Efficient price predictions of such raw materials are needed on daily basis and it is an important problem for industries as they spend several billion dollars in a year to procure such commodities for their business needs. There exists diverse and evolving information sources which can potentially influence the prices of raw materials in the markets. Multiple
machine learning based methodologies – such as non-linear regression, random forest, and expert-based learning – are present in the literature to predict the price of raw materials. However, recent research showed that artificial prediction markets can aggregate such a diverse and evolving data more effectively than the standard machine learning models (Jahedpari et al. 2017). The reason behind the success of artificial prediction market based models is that the participating agents evolve through market intelligence with time in terms of their knowledge and this leads to better price predictions. Also, our recent experiments at IBM Research confirm the effectiveness of artificial prediction markets (Jahedpari et al. 2017) in order to derive efficient price predictions using actual (diverse and evolving) data sources. Motivated by this, this tutorial provides the conceptual underpinnings of the use of artificial prediction markets for predicting raw material’s price in spot markets. Broadly the contents of this tutorial belong to the topic of collaborative decision making in the area of multi-agent systems in Artificial Intelligence.

 

Contents:

  1. Introduction to Commodity Markets (15 Minutes)
    • Commodity price index
    • Supply and Demand Balances
    • Commodities Exchange
    • Traded Commodity Classes
    • Commodity prices and price forecasts
    • Challenges associated with Price Prediction
  2. Foundational Concepts in Prediction Markets (30 Minutes)
    • What is a Prediction Market?
    • Real Examples of Prediction Markets
    • Motivation for Prediction Markets
    • Scoring Rules
    • Betting Functions
    • Artificial Prediction Markets
  3. Multi-agent based Price Prediction System (30 Minutes)
    • Problem Definition
    • Relevant Heterogeneous Data Sources
    • High Level Solution Approach
    • Architecture Diagram of Proposed System
    • Design of Artificial Prediction Market for Price Prediction
    • Performance Measures and Benchmarks
    • Comparison with respect to Popular Machine Learning Models
  4. Demo: AnyLogic Simulation Software (15 Minutes)
    • Introduction to AnyLogic
    • Multi-agent based Simulation
    • Price Prediction System Architecture
    • Demo Execution and Performance Bench-marking
  5. Conclusions and Discussion (15 Minutes)
    • Summary of the Tutorial
    • Exciting New Problems in the Area

 

Slide Materials:

Click here for AAAI 2018 Relevant Supporting Slide Materials