EPAT has been a great experience for me. It is definitely the best programme out there to learn quantitative finance and algorithmic trading. The team was and still is very helpful and caring. The course itself is a combination of different disciplines including programming, finance, and statistics taught by very knowledgeable and experienced faculty.
I recently completed the EPAT programme from QuantInsti, and it was a rich experience. I learned more here than I did on my university curriculum. This is mainly since the EPAT course is very practical and I was able to learn a lot in such a short time. It provided me with a lot of theoretical and practical knowledge in the algorithmic trading domain. Besides their excellent curriculum, the support team is friendly, dedicated, and always there to support you during your EPAT journey. They also have a placement team that keeps you updated with career opportunities. However, keep in mind that your background will influence how well you fit into those career opportunities. They also have a self-paced learning portal named Quantra which I really enjoy. Overall, they are excellent at what they do.
QuantInsti is the best place to learn professional algorithmic and quantitative trading. The EPAT programme is a highly structured and hands-on learning experience and it's being updated frequently. The faculty and staff are extremely competent and available to address any concerns you may have. Upon completion of the EPAT programme you will have the necessary tools to begin a career in algorithmic/quantitative trading.
From basic knowledge of quantitative finance to practical hands-on python session of back testing trading strategies, EPAT course covers a large portion of knowledge needed to join algorithmic trading industry. Good introduction to dive in.
The Executive Programme in Algorithmic Trading (EPAT) is a well structured, intensive course which takes approx. 6 months to complete. The core focus areas of the course are stock market theories and quantitative principles, statistical analysis and programming. With the current trend of businesses moving towards implementing Artificial Intelligence (AI) or data-centric approaches to solving difficult problems, the skills gained from this course can be used to solve any AI-related problem (i.e. these skills can be used for any domain other than algorithmic trading). Having these skills in your repertoire will likely increase the probability of finding employment. Further, the Institute actively works towards the placement of the students enrolled (or alumni) in the course. The faculty are experts in their respective fields. In order to successfully complete this course, the student must be committed to completing the assignments and projects to cement their understanding of the course material. An added advantage is that there is lifetime access to the course materials, which will enable any alumni of the EPAT course to stay updated on the developments in this field. Overall, in my opinion, EPAT provides value for your money.
I found the EPAT course to be exactly what I was looking for – the right mix of statistics, financial markets and coding. The faculties were excellent, and most importantly, the support team was exceptional with their efforts towards my learning.
Your one-stop solution for the niche and opaque domain of Algorithmic Trading. Be it faculty, student support service, training content & resources or communication, they match the standards of international repute!
I had a great experience through QuantInsti Learning. If you are passionate about Algorithmic/Quantitative Trading, or you want to start your journey in this amazing discipline, this is a great place to begin and grow your knowledge and interest. The administration and faculty were outstanding. Lectures are well-delivered and informative and there is always additional help should you require it. There is a wide array of learning material both through coursework and through the community as a whole.
Only great words to say about QuantInsti and my learning path during the EPAT programme. Always curious, always listening and improving. All the staff, starting from the CEO down to the support people were very nice 120% of the time (the 20% excess goes to all the help that they have given me after concluding the course, every time with a consistent will to help others).
Regarding the EPAT programme content, the key thing I would like to say is that is a wide covering approach. During six months, industry experts (i.e. real practitioners, not Gurus) dive into a variety of topics from scratch, so that, after that, you can choose in which field are you going to focus.
My final thoughts for new EPATians are: it is a must-do course if you are beginning in the field of algorithmic trading and quantitative finance. Although the real value is in the people that drive the institution. Be sure that you will have to take more courses after EPAT to succeed in this field, but you won't find the life-long learning support that they will give you anywhere else.
The course is very organized, both theoretical and practical, the staff is very competent and helpful, I found myself at ease during the whole course of study, I learned the basics to start a career in algorithmic trading and finance in general. What I appreciated the most were the lessons held with prominent personalities from the world of finance and trading, who shared their knowledge and experiences with the students. I would definitely recommend the course to anyone wishing to pursue a career in trading and finance.
Project work opportunity
Scholarships and Financial Aid
Lifetime access to latest course content
Verified Certification from QuantInsti and UNICOM
Exclusive Community benefits
Gain industry exposure with comprehensive Case Studies
- Knowledge of basic trading procedures and basics of algorithmic trading: know and understand the terminology
- Understand statistical methods and statistical measurements including autocorrelation function, partial autocorrelation function, Maximum Likelihood Estimation (MLE), Akaike Information Criterion (AIC), Mean Absolute Error (MAE), Root Mean Squared Error (RMSE)
- Basic knowledge of time series analysis, stationarity of time series, and forecasting using ARIMA
- Fundamentals of Autoregressive and GARCH Models, and understanding volatility
- Logistic regression to predict the conditional probability of the market direction
- Different methodologies of evaluating portfolio and strategy performance (back-testing methodologies and statistical figures for evaluation including Sharpe ratio, Sortino ratio, Max drawdown)
- Basic knowledge of Asset Allocation Models
- Understand all the most practical indicators and oscillators (e.g., RSI, MA, EMA)
- Distinguish between Macroeconomic and Microeconomic news
- Basic knowledge of models for spot prices, futures prices
- General knowledge of types of multifactor models and updating a traditional factor model
- Knowledge on the basics of the financial market in general and the stock market in particular
- A clear understanding of the type of instruments and the stock markets.
- Understand the concept of the stock market index and its calculation
- Basic knowledge of machine learning, pattern recognition as well as Natural Language Processing (NLP)
2 Module 1: Sentiment: What and Whose
- Understanding investor sentiment and the pendulum of investors’ emotions
- The role of “Noise Traders” in driving the asset prices in the financial markets
- Media sentiment and how it affects asset prices
- Market sentiment and its measurement
- Determining crowd sentiment and its impact on financial markets
3 Module 2: Sentiment Data
- Classical newswires and macroeconomic announcements
- Various Sources of sentiment data such as news, social media, and search engines
- The impact of Micro-blogging platforms on stock markets
- Converting qualitative information to the sentiment score
- Using bag-of-words, natural language processing and lexicon-based methods in sentiment analysis
4 Module 3: Structure and Coverage
- News analytics (Meta) data structure
- The exact polarity of sentiment in the news
- News characteristics such as relevance, novelty, and sentiment scores
- Leading data providers for sentiment data analysis in finance
- Description of the data provided by major sentiment vendors
5 Module 4: Other Sources: Alternative Data
- Scheduled (expected) and Unscheduled (unexpected) financial news
- Macroeconomic news and their usage in automated trading
- Relevance and use of alternative data in sentiment analysis
- Major types of alternative data
- Different categories of alternative data such as satellite data, geolocation data, etc.
- Providers of alternative data
6 Module 5: Models to Exploit Sentiment Analysis (I)
- Taxonomy of models
- Descriptive, normative, prescriptive and decision models explained
- Modelling and information architecture
- Examples of modelling in the domain of finance
- The key role of time and uncertainty in decision making
7 Module 6: Models to Exploit Sentiment Analysis (II)
- Financial applications of sentiment data and their properties
- Risk management through risk quantification: risk computed for exposures of varying time spans, namely, weekly, monthly, or annualized
- Fund rebalancing on calendar dates: weekly, monthly, yearly
- Automated trading daily or intraday
- Retail application (creditworthiness, loan, and savings advice)
8 Module 7: Opinion and Biases
- Various challenges in the area of sentiment analysis
- Distinction between opinions and facts
- Role of behavioural finance in investor decision making
- Different types of biases that affect investor behaviour in financial markets
- Revisiting the pendulum of fear and greed
9 CSAF Exam
- CSAF requires you to successfully clear the Examination
- The exam is conducted in a proctored environment both at the Prometric centres in 80+ countries and remotely
1 Asset Allocation Strategies: Enhanced by News
- Trading Strategy and Sentiment Analysis
- Market Data and News Meta Data Analysis
- Asset Allocation Strategy
- Construction of Filters and its applications
- Empirical Investigation
2 Forecasting crude oil futures prices using global macroeconomic news sentiment
- Impact of crude oil price variation
- Forecasting arbitrage-free (futures) prices
- Macroeconomic news analytic data
- Models for spot prices and futures prices
- Kalman filter and removal of noise
- Analysis, estimation, and forecasting results
3 Asset Allocation Strategies: Enhanced by Micro-Blog
- Trading Strategy & Sentiment Analysis
- Market Data and Micro-blog Sentiment Data
- Asset Allocation Strategy
- Construction of Filters
- Application of Filters
- Empirical Investigation and Back-testing Results
4 Improved Volatility Prediction and Trading using Sentiment
- Volatility prediction
- Market Data and Micro-blog Sentiment Data
- Impact Scores from Sentiment
- GARCH & ARCH Model
- Metrics for Evaluation
- Evaluation of model performance
5 Equity portfolio risk estimation using market information and sentiment
- Understanding equity price uncertainty
- Update a traditional factor model
- Types of multifactor models
- Updating model volatility using quantified news
- Computational experiments
6 An Impact Measure for News: Its Use in (Daily) Trading Strategies
- Impact of News & Sentiment
- Designing equity trading strategies
- Return, Volatility and Liquidity Measures
- Sentiment Measure & Impact score
- Autoregressive and GARCH Models
- Experimental trading results
Anthony Luciani is a Senior Quantitative Analyst at MarketPsych. He is working on simplified sentiment and “Superforecasters” models. He developed sentiment-based financial models, previously for Optirisk. He has a Master’s Degree in Financial Mathematics from the University of Leicester.
Prof. Christina Erlwein-Sayer
Prof. Christina is Professor of Statistics and Financial Mathematics at Hochschule für Technik und Wirtschaft (HTW) Berlin and has worked at OptiRisk Systems as a quantitative analyst and senior researcher. She completed her PhD in Mathematics at Brunel University, London in 2008. She then worked as a researcher and consultant in the Financial Mathematics Department at Fraunhofer ITWM, Kaiserslautern, Germany.
Dr. Cristiano Arbex Valle
Dr. Valle has a bachelor’s degree in Computer Science and an MSc in Operations Research from Universidade Federal de Minas Gerais (UFMG), Belo Horizonte, Brazil. In 2011 he joined OptiRisk as a software engineer and a researcher and obtained his PhD in the Department of Mathematical Sciences from Brunel University (UK) in 2014.
Dan Joldzic, CFA, FRM is CEO of Alexandria Technology, Inc, which develops artificial intelligence to analyse financial news. Prior to joining Alexandria, Dan served dual roles as an equity portfolio manager and quantitative research analyst at Alliance Bernstein where he performed factor research to enhance the performance of equity portfolios.
Prof. Enza Messina
Prof. Enza Messina is a Professor in Operations Research at the Department of Informatics Systems and Communications, University of Milano-Bicocca, Italy, and holds a PhD in Computational Mathematics and Operations Research from the University of Milano. She is a co-founder of Sharper Analytics, a spin-off from the University of Milano Bicocca.
Prof. Gautam Mitra
Prof. Mitra is an internationally renowned research scientist in the field of Operational Research in general and computational optimization and modelling in particular. He is the founder and chairman of OptiRisk Systems and UNICOM seminars. He has published five books and over a hundred and fifty research articles and was awarded the title of ‘distinguished professor’ by Brunel University in 2004.
Dr. Matteo Campellone
Dr. Matteo is the co-founder and Executive Chairman of Brain. He holds a PhD in Physics and an MBA. Dr. Matteo’s past activities included Financial Modelling for financial institutions and Corporate Risk and Value-Based Management for industrial companies. As a Theoretical Physicist, he worked in the field of statistical mechanics of complex systems and of non-linear stochastic equations.
Dr. Ravi Kashyap
Dr. Kashyap is experienced working as a Product Manager and a Quantitative Strategist working for financial services companies, namely, Goldman Sachs, Morgan Stanley, Merrill Lynch, Citigroup and IHS Markit. He holds a PhD from the City University of Hong Kong. He was a finance professor at SolBridge International School of Business, South Korea and subsequently with SP Jain School of Global Management, Singapore.
Dr. Richard Peterson
Dr. Peterson is CEO of MarketPsych Data which produces psychological and macroeconomic data derived from text analytics of news and social media. He is an award-winning financial writer, an associate editor of the Journal of Behavioral Finance, has published widely in academia, and performed postdoctoral neuroeconomics research at Stanford University.
Shradha is a Data Scientist and Research Analyst at OptiRisk Systems. She holds a Bachelors in IT from Meghnad Saha Institute of Technology, Kolkata, India and a Masters in Data Science and Analytics from Brunel University, London. She has over 5 years of experience in software development with TCS, India. She holds certifications in Java, Oracle SQL and SAS; she is also competent in R and Python and analytical tools like Tableau and Power BI.
Dr. Zryan Sadik
Dr. Sadik holds a Bachelors in Mathematics from Salahaddin University, Iraq, a Masters in Computational Mathematics with Modelling and a PhD in Applied Mathematics from Brunel University, London (2018). His research interests include news sentiment analysis, filtering in linear and nonlinear time series applying Kalman filters, volatility forecasting, optimization, risk assessment, and the role of news sentiment in financial markets.
Get on a call
with a Counsellor
Pay the fee
and get started
Before admission, we will facilitate a one-on-one counselling session that will focus on understanding the strengths and weaknesses of the participant. These sessions do not necessarily decide the participants' eligibility but help counsellors assist them with informed guidance prior to enrollment.