CAMPUS QUANT & DATA SCIENCE

The learning carried out in this CAMPUS QUANT & DATA SCENCE involves applying the techniques used by large investment funds, explained intensively in 8 weeks, which will qualify you as a Quant Trader. It is a practical and intuitive training divided in three stages, starting with the first strategies for the automation and the generation of new strategies by data mining techniques. Once the investment model has been detected, we will start the process of creating a portfolio of strategies developed in Python code. Finally, we will move the strategies created in previous phases into production. For this we will use classifiers and other artificial intelligence techniques.

1 GENERATION OF PATTERNS AND NEW STRATEGIES BY DATA MINING TECHNIQUES

This highly technical training begins with a two-week introduction to programming applied to quantitative finance and the use of tools for developing trading strategies based on learning and generating patterns by data mining techniques and their continuous improvement through iterative techniques.

We will start with simple platforms that are intuitive to use and then move on to institutional platforms, which will be a turning point in the way you see and understand trading systems. Nowadays, data mining techniques and artificial intelligence generate what is beginning to be known as artificial imagination, that is, when it is the machine that proposes investment ideas at the same time as it carries out tests and iterations on different solutions to find optimised alternatives. In this block we will lay the foundations so that you can take advantage of these technologies.

BLOCK 1

MODULE I: INTRODUCTION TO PROGRAMMING IN FINANCE

In this first phase we will look at the basic concepts of finance and will be introduced to the different platforms with one of the main languages used by them. We will look at the different market data available and create an Expert Advisor based on examples. This Expert Advisor will be optimised using the MT4 strategy tester.

1 INTRODUCTION TO FINANCE. THE MARKET
2 MARKET INDICATORS
3 INVESTMENT PLATFORMS. MT4 LANGUAGE
4 PRACTICE: CREATION OF AN MT4 INDICATOR
5 INTRODUCTION TO BIG DATA ANALYTICS
6 PRACTICE: REALISATION OF AN MT4 EXPERT ADVISOR
7 PRACTICE: BACKTESTING IN MT4. PARAMETER OPTIMISATION

MODULE II: TRADING STRATEGY DEVELOPMENT TOOLS

In the second phase we will see the different tools provided by the specific software for trading strategies. Using this software, without the need for programming, we will test the first group of strategies by applying the logic of our Expert Advisor created in the previous phase.

1 STRATEGY-SPECIFIC SOFTWARE
2 MANUAL FOR THE USE OF SPECIFIC STRATEGY SOFTWARE PROGRAMME
3 TOOL A.W. OF THE SPECIFIC STRATEGY SOFTWARE
4 PRACTICE: SWITCHING FROM AE MT4 TO A.W.
5 SIGNAL ANALYSIS ON TRADING STRATEGY PLATFORMS
6 ANALYSIS OF THE DATA OBTAINED IN A.W.
7 TOOL B. OF THE STRATEGY SPECIFIC SOFTWARE
8 PRACTICE: PASSAGE FROM EA MT4 TO B
9 ANALYSIS OF THE DATA OBTAINED IN B
10 TOOL R. OF THE SPECIFIC STRATEGY SOFTWARE

2 GENERATION OF AUTOMATED TRADING STRATEGIES: AGENT MODEL

We will go deeper into different strategy generation techniques, those based on artificial learning and those based on random searches through evolutionary processes. Once the investment model has been detected, we will apply different optimisation techniques in order to understand in which markets, situations and configurations to use these models. Finally, we will begin the process of creating a portfolio of strategies that we will put to work as a block, so that a portfolio of strategies will have certain advantages over the use of a single strategy, as the results curve is smoothed and the generation of results is optimised. You will have the necessary support to build, parameterise and properly use these strategy portfolios built in Python.

BLOQUE 2

MODULE III: STRATEGY GENERATION. ARTIFICIAL LEARNING TECHNIQUES

In the third phase we will see the programmes necessary for downloading the database for our testing and we will carry out the first group of strategies using the agent modelling technique. Strategies needed later for our final portfolio.

1 ACCESS TO QUALITY TEST DATABASES
2 INITIAL POPULATION REALISATION OF STRATEGIES BY GENETIC EVOLUTION (AGENT MODEL)
3 TESTER OF THE INITIAL POPULATION OF STRATEGIES I

MODULE IV: STRATEGY GENERATION. RANDOM SEARCH TECHNIQUES

In the fourth phase, the second group of strategies will be realised using the random search technique for trading signals. These strategies are then needed for our final portfolio.

1 REALISATION OF THE INITIAL POPULATION OF STRATEGIES BY RANDOM GENERATION
2 TESTER OF THE INITIAL POPULATION OF STRATEGIES II

MODULE V: BUILDING A PORTFOLIO OF STRATEGIES

In the fifth phase, using the previous two groups of strategies and selecting the best ones to create a base group, you will be trained to create the first portfolio of trading strategies using the specific strategy software.

1 CRITERIA FOR THE SELECTION OF BASIC STRATEGIES FOR PORTFOLIO BUILDING
2 RELEVANT PARAMETERS IN SPECIFIC HIGH-LEVEL SOFTWARE INDICATORS AND SIGNALS
3 GENERATION OF NEW TRADING STRATEGIES FROM THE INITIAL PORTFOLIO
4 TESTER GENERATED STRATEGIES

3 ARTIFICIAL INTELLIGENCE

In this last phase, which lasts 3 weeks out of a total of 8 weeks of training, we will dedicate ourselves to put the strategies created in previous phases into production, i.e. we will define the steps to be taken to start using an automatic strategy in real life and how to scale results. Each development must go through different validation phases before being used in fund management. Furthermore, the transition to production is a key aspect in the success of the process.

To do this we will use classifiers and other artificial intelligence techniques that will help us to weight the risk assumed by each strategy, and by the overall risk of our portfolio, depending on the moment of the market, that is, we will have a statistic of when each of the strategies works best and we will apply risk management adapted to each situation. The learning carried out in this CAMPUS QUANT & DATA SCENCE involves applying the techniques used by large investment funds, explained intensively in 8 weeks and that will qualify you as a Quant Trader.

BLOCK 3

MODULE VI: OPTIMISATION PROCESS

In the sixth phase, using the Software O. tool, the selected strategies will be studied and worked on and optimised by IA and Clustering methodology.

1 INTRODUCTION TO HIGH-LEVEL SOFTWARE O
2 OPTIMISATION METHODS I
3 OPTIMISATION METHODS II
4 OPTIMISATION METHODS III
5 ANALYSIS OF A LIVE SESSION

MODULE VII: ARTIFICIAL INTELLIGENCE TECHNIQUES TO IDENTIFY HIGH-PROBABILITY SITUATIONS

In the seventh phase, using AI classifier theory, the best trading sessions will be identified and characterised using the developed portfolio of strategies.

1 INTRODUCTION TO IA
2 INTELLIGENT ENTITIES. CLASSIFIERS IN IA
3 CLASSIFIER LEARNING
4 OPTIMISATION OF RISK MANAGEMENT BY INTELLIGENT ALGORITHMS

MODULE VIII: TRANSITION TO PRODUCTION

In the eighth phase, finally, you will see how to visualise the pseudocode of the optimised strategies and how to obtain the code in different languages in order to validate it and pass it live on the head-end platform used.

1 CHARACTERISATION OF OPTIMISED STRATEGIES
2 VALIDATION AND TRANSITION TO ACTUAL
3 HIVE MIND

WHAT ARE THE CLASSES LIKE?

Video classes

The core content of the training is recorded on video, with PDF support and a broker simulator to download so that you can study the key concepts of the operation at any time. You have a tutor who will help you with whatever you need at all times.

Live practical explanations

The practical explanations are carried out in live broadcasts, and you can ask questions live. If you are unable to attend, they will be recorded and you will be able to watch them later, as well as resolve any doubts you may have.

Upgrades and lifetime access to the private discord group

The training is structured in phases with objectives to be achieved, in which the tutors provide follow-up and answer questions through the private group of Quant students on discord, where you can also interact with other students from all over the world and keep up to date, as online access is maintained indefinitely at the end of the training.

UNIVERSITY CERTIFICATION

· Quant Trader Data Science Expert Certification
Admission requirements: admission interview (limited places)

· Official Doctorate Degree in Big Data for Finance + Data Science Expert Quant Trader Certification
Admission requirements: official master’s degree and admission interview (scholarships)

* Optionally, for a fee of €580, a fee for the issuing of the degree. It is sent apostilled and legalised for recognition between countries.

FORTHCOMING CALLS