Predicting Stock Prices with Multi-Layer Perceptron

Slides:



Advertisements
Similar presentations
Neural Networks in Financial Analysis
Advertisements

Sophomore Slumpware Predicting Album Sales with Artificial Neural Networks Matthew Wirtala ECE 539.
Scott Wiese ECE 539 Professor Hu
Charles Rodenkirch December 11 th, 2013 ECE 539 – Introduction to Artificial Neural Networks PREDICTING INDIVIDUAL PLACEMENT IN COLLEGIATE WATERSKI TOURNAMENTS.
Rate Earned on Average Total Assets n (January 1 Total assets + December 31 Total Assets) / 2 = Average Total Assets n Net Income after Federal Income.
GET RICH QUICK CO. Financial Statement Ratio Analysis: Profitability Long-Term Financial Position Short-Term Financial Position.
By Charles A. Clark1 ANN Approach to Revenue or Profit Estimation University of Wisconsin-Madison.
Neural Networks Dr. Peter Phillips. Neural Networks What are Neural Networks Where can neural networks be used Examples Recognition systems (Voice, Signature,
VALUATION AND FORECASTS
Chapter 14.  To make informed decisions about a company  Generally based on comparative financial data 2Copyright (c) 2009 Prentice Hall. All rights.
Twitter Volume Spikes: Analysis and Application in Stock Trading Yuexin Mao, Wei Wei and Bing Wang COMP4332/RMBI4310 CHAN Chun Ting ( )
Enterprise Value What is Enterprise Value? –Market Value of Equity plus debt minus cash and investments Why is it used? –To more accurately reflect the.
Financial Statement Analysis
Stock Value Ratio Classification Yan SuiZheng Chai.
A Neural Network Approach to Predicting Stock Performance John Piefer ECE/CS 539 Project Presentation.
Buy or Sell? The age old question. Introduction Goals: Predict stocks one year out with a MLP Predict stocks one year out with a MLP Prove you only need.
Data Mining Techniques in Stock Market Prediction
CENTURY 21 ACCOUNTING © Thomson/South-Western LESSON 13-2 Financial Statements and Analysis.
CENTURY 21 ACCOUNTING © 2009 South-Western, Cengage Learning LESSON 13-2 Financial Statements and Analysis.
Business Valuation What’s an apple tree worth?.
CENTURY 21 ACCOUNTING © 2009 South-Western, Cengage Learning LESSON 17-2 Calculating Earnings Performance and Efficiency Analysis.
Ratios and Accounting A 1 to 1 training course (get it!)
Chapter 3 Financial Statement Analysis. Financial Statement Analysis, Some Background Financial statements reflect the results of actions taken by the.
Prediction of the Foreign Exchange Market Using Classifying Neural Network Doug Moll Chad Zeman.
Artificial Neural Networks Approach to Stock Prediction Presented by Justin Jaeck.
23-1 Intermediate Accounting James D. Stice Earl K. Stice © 2012 Cengage Learning PowerPoint presented by Douglas Cloud Professor Emeritus of Accounting,
 52-Week Hi & Low  Highest & lowest selling price of the stock during the preceding 52 week  Company Name/Name of Stock  Ticker Symbol  Unique alphabetic.
Estimation of car gas consumption in city cycle with ANN Introduction  An ANN based approach to estimation of car fuel consumption  Multi Layer Perceptron.
Stock market forecasting using LASSO Linear Regression model
Artificial Neural Networks for Data Mining. Copyright © 2011 Pearson Education, Inc. Publishing as Prentice Hall 6-2 Learning Objectives Understand the.
BANK PERFORMANCE MAJOR FACTORS THAT AFFECT A BANK’S PERFORMANCE.
Valuing a Company What determines a companies worth?
Neural network based hybrid computing model for wind speed prediction K. Gnana Sheela, S.N. Deepa Neurocomputing Volume 122, 25 December 2013, Pages 425–429.
FACILITIES PLANNING ISE310L SESSION 15 Chapter 14, March 7, 2016 Geza P. Bottlik Page 1 OUTLINE Questions? Stories or experiences? Advice for the project.
Stock Market Basics What you need to know…. What is a Stock? A stock is a piece of a company If you own a “stock” that means that you actually own a piece.
Accounting: What the Numbers Mean Study Outline and Overhead Master Chapter 11.
Prepared by Fayes Salma.  Introduction: Financial Tasks  Data Mining process  Methods in Financial Data mining o Neural Network o Decision Tree  Trading.
A beginner’s guide.  Prev Close:  Open: 106  1y Target Est:  Day’s Range:  52wk Range:
Chapter 3 - Evaluating a Firm’s Financial Performance
Historical Performance Analysis
Financial Statement Analysis
Demonstration Problem
Intermediate Financial Accounting Earl K. Stice James D. Stice
Financial Statement Analysis
Outline Problem Description Data Acquisition Method Overview
Analysis Example Financial Ratio
Computer Science and Engineering, Seoul National University
Buying Fashion Fashion Marketing.
과제 3: 인공신경망.
Multi-Layer Perceptron On A GPU
Neural Networks Dr. Peter Phillips.
NEURAL NETWORK APPROACHES FOR AUTOMOBILE MPG PREDICTION
User Location Prediction using MLPs
Genetic Algorithm Optimization for Selecting the Best Architecture of a Multi-Layer Perceptron Neural Network. A Credit Scoring Case Alejandro Correa,
Training a Neural Network
Buying Fashion Fashion Marketing.
Prediction of Wine Grade
DOE Oil Price Forecasts
Lesson 13-2 Financial Statements and Analysis
AirBnB Pricing Predictions
Yi Zhao1, Yanyan Shen*1, Yanmin Zhu1, Junjie Yao2
Visualizing and Understanding Convolutional Networks
Drive Time Average and Variation Estimator
Neural Networks II Chen Gao Virginia Tech ECE-5424G / CS-5824
Neural Networks II Chen Gao Virginia Tech ECE-5424G / CS-5824
Lesson 13-2 SHARE OF NET INCOME ASSIGNED TO PREFERRED AND COMMON STOCK
Predicting Voter Choice from Census Data
FIMO Video Presentation
LSTM Practical Exercise
Presentation transcript:

Predicting Stock Prices with Multi-Layer Perceptron Raamis Hussain

Outline Try to predict daily closing price of Apple stock using various features Date, daily open, daily high, daily low, price/earnings ratio, market capitalization, volume Predict trends as well as actual price using 1200 days of data

Configuring MLPRegressor 1-3 hidden layers Rectified Linear Unit Function as activation function: f(x) = max(0, x) Stop when validation score stops improving

Predicting Price Trends Try to predict general price movement over some time period Success = predicting positive/negative change Use date as only feature

Predicting Price Trends

Success! We are able to accurately predict the general trend of the price using our MLP Next step: Train MLP with features and try to predict actual price Train features for closing price 15 days in the future

15-Day Prediction Test

Doesn’t Work! The Neural network is making predictions of the past instead of the future Apparently the features are too closely related to same-day price MLP predicting closing price of day on same day as given features Try with less features

15-Day Prediction Test #2 Features: Date, p/e ratio, market cap, volume

Conclusions Even with features that are not related to the price, the prediction isn’t very accurate MLP predicts same-day price instead of future price We need more general and sophisticated features to train on Earnings per share Debt to equity ratio And others Our simplistic method is not sophisticated enough to predict exact stock prices