Financial data forecasting has historically been a significant domain with a wide array of consequences and applications. In today’s tech driven era, it has facilitated the prevalence of data-driven decision making, reduced uncertainties in the financial arena and propelled monetary profits unprecedentedly. Numerous techno-social algorithms and technologies have been employed to facilitate financial data forecasting. Modelling these forecasters is not easy since financial markets are unpredictable, noisy, non-linear and volatile. However, the implementation of machine learning can prove to be vital. Many researchers across the globe have attempted to use sophisticated machine learning models to predict stock prices and stock price movements accurately.
In order to adopt a more holistic approach to stock price prediction, this talk will cover prediction of of selected small-cap and large-cap stocks/ indexes. Furthermore, in this talk, we will explore and experiment different combinations of input features which generate lowest error. Finally, various machine learning and deep learning models are explored and evaluated to discover the most accurate and reliable model.
Outline
INTRODUCTION
-Introduce myself and my background
-Explain my motivation behind choosing this topic
-Introduce the topic and its significance
OVERVIEW OF METHODOLOGY
-Data collection
-Data preprocessing and analysis
-Creation of new features: Technical Indicators and Sentiment Analysis
-Feature Engineering: Principal Component Analysis (PCA) and Recursive Feature -Elimination (RFE)
-Machine learning/ deep learning: LSTM, LR, SVM etc.
DATA COLLECTION
-Introduce the kinds of data collected and the reason behind doing so
-Numeric Data: Historic prices from Yahoo Finance
-Non-Numeric Data: News Headlines from Reuters.com
DATA PREPROCESSING AND ANALYSIS
-Scaling
-Missing values
-Plotting graphs
-Correlations
TECHNICAL INDICATORS AND SENTIMENT ANALYSIS
-Technical indicators: Simple Moving Average (SMA), Exponential Moving Average (EMA), -Relative Strength Index (RSI)
-Polarity scores using VADER’s Sentiment Intensity Analyzer
-Subjectivity scores using TextBlob
-Headline embedding using Google’s Universal Sentence Encoder
FEATURE ENGINEERING
-Dimensionality reduction using Principal Component Analysis (PCA)
-Feature Selection using Recursive Feature Elimination (RFE)
LONG SHORT TERM MEMORY
-What is LSTM?
-Why do we pick LSTM over other algorithms?
-Implementation
-Optimization of hyperparameters and parameters
-Testing
RESULTS AND DISCUSSION
-Discuss the results
-Q&A
Speaker: Ms. Anshika Rajiv / Hong Kong / Computer Science Student at the University of Hong Kong (HKU) - Website, GitHub, Facebook Language: English Date and Time : October 9, 2021 / 11:15-11:45 (UTC+8)
Speaker Introduction
Anshika Rajiv is a final year student at the University of Hong Kong (HKU), one of the top universities in the world. Here, she is studying on a 100% scholarship and is majoring in Computer Science with a minor in Information Systems. Born and raised in India, Anshika was a part of the top 0.1% achievers in CBSE board examinations. She has also been awarded a gold medal for her excellent academic performance.
Previously, Anshika has interned at big organizations such as J.P Morgan Chase & Co. as well as fintech startups. She has the experience of studying and working in India, Hong Kong, the Philippines, London and Singapore.
Anshika is passionate about new technologies especially in the fields of machine learning and deep learning. She started coding in python in first year of university and since then, she has taken up numerous projects and competitions. Additionally, she strongly believes in empowering women and wants to encourage more girls to take up coding. She is 1 of 4 girls from all universities in Hong Kong to be selected for the Credit Suisse Inspire Women in IT program. Moreover, she is currently authoring a paper on Underrepresentation of Girls in STEM related fields.