A finance student versus a professional trader

1. Traditional stochastic models vs AI (machine learning and deep learning).

Algorithmic approach:

• Traditional stochastic models: These models rely on explicit mathematical algorithms that are often based on simplifying assumptions about data distribution. They use methods such as linear models, time series, ARIMA (AutoRegressive Integrated Moving Average) models, etc.

• AI (machine learning and deep learning): These approaches rely on learning from data rather than on the explicit specification of a mathematical model. Models are trained to recognize patterns and relationships in data using machine learning algorithms, and in the case of deep learning, through artificial neural networks with multiple hidden layers.

Ability to capture complex models:

• Traditional stochastic models: They are often less able to capture complex, non-linear patterns in the data because they rely on simpler assumptions and less flexible model structures.

• AI (machine learning and deep learning): These approaches are better suited for capturing complex, non-linear patterns in data, thanks to their ability to learn hierarchical data representations at various levels of abstraction.

Interpretability:

• Traditional stochastic models: They are often easier to interpret because they are based on explicit mathematical formulas.

• AI (machine learning and deep learning): These models are often more difficult to interpret due to their complex nature and opacity. However, there are techniques to explain the predictions of these models, but they can be more complex to implement.

Data requirements:

• Traditional stochastic models: They can often work with relatively small data sets and can provide reasonable results even with missing or noisy data.

• AI (machine learning and deep learning): These approaches generally require larger data sets for training, and they are often sensitive to data quality and quantity. They may require more data preprocessing to get meaningful results.

2. Is the LSTM RNN (multivariate) model best for stock market forecasting? What data should you use: high, low, open, open, close, volume + corporate data?

The LSTM (Long Short-Term Memory) RNN (Recursive Neural Network) model is indeed one of the popular models for forecasting time series, including stock market data. However, there is no single model that is always the “best” for stock market forecasting, as the effectiveness of a model depends on many factors, including the quality and quantity of available data, the forecast period, and the changing nature of financial markets.

Data commonly used for stock market forecasting generally includes stock prices (high, low, open, close), trading volume, and relevant macroeconomic data. Additionally, using corporate data such as financial reports, product and service data, business-specific events, etc., can also be useful in improving prediction performance.

Here are some important considerations when using an LSTM RNN model for multivariate stock market forecasting:

• Choice of features: It is important to select wisely which features to include in the model. This may include stock prices (high, low, open, close), trading volume, and other relevant data such as business data (e.g. revenue, earnings, profits, major announcements).

• Data preprocessing: Before training the LSTM model, it is essential to normalize the data, deal with missing values, and possibly apply smoothing or noise reduction techniques.

• Model architecture: The architecture of the LSTM model may vary depending on data complexity and specific forecasting needs. This may include the number of LSTM layers, the number of neurons in each layer, as well as the use of techniques such as attention to improve model performance.

• Model training and validation: Training the LSTM RNN model involves dividing the data into training and validation sets, and tuning the hyperparameters of the model to optimize forecasting performance. Using techniques such as cross-validation can help assess the generalizability of the model.

3. What historical period should you choose for a specific prediction horizon?

Choosing the historical period to train a prediction model depends on several factors, including:

• Stable market conditions: Financial markets can be subject to periods of volatility or stability. It is often a good idea to choose a historical period that represents a variety of market conditions, including periods of rise, fall, and stability, so that the model is able to generalize effectively to different situations.

• Data availability: Available historical data may have limitations in terms of availability and quality. It is important to choose a historical period for which you have good quality and complete data, so that the model can be properly trained.

• Temporal relevance: If you plan to predict in the short term, it may be useful to use more recent historical data as it is more likely to reflect current market conditions. On the other hand, if your prediction horizon is longer term, you can use a wider historical period to capture longer-term trends.

• The prediction objective: The historical period chosen may also depend on the specific objective of your prediction. For example, if you are focused on predicting short-term volatility, you can choose a historical period that includes periods of high volatility. If you are predicting long-term trends, a longer historical period may be appropriate.

In summary, the choice of the historical period depends on a variety of factors, including the stability of market conditions, data availability, temporal relevance, and the objective of prediction. It is important to choose a historical period that represents a variety of market conditions and that is adapted to the specific prediction horizon.

4. Passive investment (ETF) vs stock selection: long-term performance (mention of hedge funds).

When comparing passive investment via ETFs (Exchange-Traded Funds) to active stock selection, especially with respect to long-term performance, several factors need to be taken into account, including risk management, costs, and the effectiveness of fund managers.

Passive investment (ETF):

• ETFs generally follow market indices, which means that their performance is linked to that of the underlying index. They offer instant diversification since they invest in a basket of stocks that are representative of the index.

• ETF management fees are generally lower than actively managed funds, which can increase net returns for long-term investors.

• Passive investors generally benefit from the stability of long-term investments and often avoid the volatility associated with active stock selection.

Active selection of titles:

• Active stock selection involves fund managers choosing individual stocks in an effort to outperform the market. This can lead to higher-than-market returns if managers make smart choices.

• However, research shows that most fund managers fail to consistently beat the market over the long term after accounting for management fees.

• Some funds like hedge funds use more sophisticated strategies, such as arbitration, derivatives trading, or the use of leverage to try to generate higher returns. However, these strategies may be riskier and less accessible for ordinary investors.

In general, ETFs often offer a simple, low-cost, and diversified investment option for long-term investors, while active stock selection can involve higher risks and greater costs. While some fund managers may outperform the market, most investors opt for passive strategies because of their efficiency and simplicity. However, each investor should assess their own goals, risk tolerance, and preferences before choosing an investment approach.

5. What are the main causes of increases in the financial markets? What main indicators to watch out for? (financial ratios, liquidity on the markets: monetary policy of central banks).

Rises in financial markets can be caused by a variety of economic, financial, and geopolitical factors. Here are some of the main causes of increases in the financial markets and the main indicators to watch out for:

1. Economic growth: Strong and sustained economic growth can boost investor confidence and encourage increases in financial markets. Investors monitor indicators such as gross domestic product (GDP), employment numbers, consumer spending, and business confidence indicators to assess the health of the economy.
2. Accommodative monetary policy: Accommodative monetary policies by central banks, such as low interest rates and monetary stimulus measures such as quantitative easing, can encourage investments in financial markets by making credit cheaper and stimulating economic activity.
3. Business earnings outlook: The positive outlook for corporate earnings can help support increases in financial markets. Investors monitor quarterly company reports, earnings growth prospects, and sector-specific indicators to assess future business performance.
4. Political and geopolitical stability: Political and geopolitical stability in a given region can also encourage increases in financial markets by reducing uncertainty and increasing investor confidence.
5. Cash flow: Cash flows in financial markets, including inflows of foreign capital, asset purchases by investment funds, and movements by institutional investors, can also influence price movements in markets.

In terms of the main indicators to watch out for, here are some of the main ones:

• Stock market indices: Stock market indices such as the S&P 500, the Dow Jones Industrial Average, and the Nasdaq Composite are often used as barometers of overall market performance.
• Interest rate: Interest rates set by central banks are closely monitored because they influence the cost of credit and can have an impact on investment decisions.
• Inflation: Inflation can affect purchasing power and real investment returns. Investors monitor inflation trends and central bank monetary policy decisions in response to inflation.
• Economic indicators: Indicators such as GDP, employment figures, retail sales, and the Purchasing Managers Index (PMI) can provide insights into the health of the economy and influence investment decisions.
• Financial ratios: Financial ratios such as price-to-earnings ratio (PER), price-to-book ratio (P/B), and dividend yield can be used to assess stock valuation and guide investment decisions.

In summary, increases in financial markets can be influenced by a wide range of economic, financial, and geopolitical factors. Investors are closely monitoring key economic indicators, central bank monetary policies, and liquidity flows in the markets to assess the prospects for growth and returns.

6. How to escape the algorithms of Black Rock, Citadel, etc.? What mentality and what strategy should we adopt?

Escaping the algorithms of asset management firms such as BlackRock and Citadel can be difficult, as these firms use sophisticated strategies and advanced algorithms to make investment decisions. However, here are some approaches that some investors are taking to try to stand out:

1. Adopting a long-term approach: Instead of looking to beat algorithms in the short term, investors can take a long-term approach by investing in solid companies with solid fundamentals. This approach can help avoid short-term fluctuations and focus on long-term growth.
2. Investing in alternative assets: Investors may choose to invest in alternative assets such as real estate, commodities, or private investments, which may be less influenced by the high-frequency trading algorithms used by some asset management firms.
3. Portfolio diversification: Portfolio diversification is a key strategy for mitigating risks associated with market movements. By investing across a broad range of assets, sectors, and geographic regions, investors can reduce their exposure to price fluctuations influenced by algorithms.
4. Focus on intrinsic value: Instead of blindly following market movements, investors can focus on the intrinsic value of the assets they hold. This involves conducting a thorough analysis of the company's fundamentals, including its revenue, earnings, management, and competitive position.
5. Socially responsible investment (SRI): Socially responsible investing takes into account environmental, social and governance (ESG) criteria in the investment process. This approach can help investors avoid businesses that don't meet ethical or environmental standards.
6. Mentoring and continuing education: Investors can seek out experienced mentors and continue to train to improve their investment skills. Understanding markets, investment strategies, and economic trends can help investors make informed decisions and stay informed about market developments.

7. Are financial market rules changing? (current inconsistencies)

Demographics, the proliferation of fake news, and hidden interests in an information war context can influence financial market rules and create regulatory inconsistencies. Here's how these aspects can impact financial markets:

1. Demographics: Demographic trends, such as an aging population, changes in family structure, and international migration, can impact financial markets by influencing demand for goods and services, economic growth, and fiscal policies. For example, an aging population may lead to increased demand for financial products related to retirement, while international migration may affect cross-border capital flows and investments.
2. Fake news and misinformation: The proliferation of fake news and misinformation can have an impact on investor confidence and the stability of financial markets. Misinformation can influence investment decisions, create irrational price movements, and disrupt market stability. Financial regulators may need to adopt rules to promote transparency and combat misinformation in financial markets.
3. Information warfare and hidden interests: In a context of information warfare, state and non-state actors may seek to manipulate financial markets to serve their own political or economic interests. This may include spreading false information to destabilize markets, manipulating financial asset prices, or using economic sanctions to influence investor decisions. Financial regulators must be vigilant in detecting and countering such practices in order to maintain the integrity of financial markets.
4. Increase in the money supply: The increase in the money supply may result from expansionary monetary policies put in place by central banks to stimulate the economy. This can lead to increased levels of liquidity in financial markets, which can affect asset prices and require tighter regulation to prevent financial bubbles and systemic risks.
5. Dematerialization of financial transactions: The dematerialization of financial transactions, facilitated by technology and digital platforms, can make it more difficult for regulators to monitor and regulate activities in financial markets. This can create regulatory gaps that require adjustments to ensure transparency and regulatory compliance.
6. Lack of real compensation for certain non-traceable products: Some financial products, such as complex derivatives or cryptocurrencies, may lack a real physical counterpart or an objective assessment of their intrinsic value. This can make it difficult for regulators to determine the risks associated with these products and to put in place effective regulations to monitor and control them.

In response to these challenges, financial regulators may seek to put in place stronger rules for managing the money supply, monitoring electronic transactions, and regulating complex financial products. They may also seek to promote the transparency and accountability of market participants to reduce systemic risks and protect investors.

However, due to the complex and globalized nature of financial markets, it can be difficult to develop rules that manage to effectively regulate all aspects of financial activities. This can lead to regulatory inconsistencies and gaps, requiring constant supervision and adaptation by financial regulators.

8. Are the concept of Drift (mu) and Mean Reverting the most important? Universal laws of nature?

The concept of drift and mean reversion are two important concepts in finance, but they are not necessarily the only ones or the most important ones. However, they reflect fundamental aspects of financial markets that may be influenced by universal principles observed in nature. Here is an overview of these concepts and their relevance:

1. Drift (mu): Drift refers to the overall trend or average growth of a financial asset over a given period of time. In simple terms, it is the average expected growth rate of the asset. This trend can be influenced by a variety of factors such as economic growth, monetary policies, technological innovations, etc. Understanding the drift of an asset is important in order to assess its expected return and to make appropriate investment decisions.
2. Mean reversion: The concept of a return to the mean suggests that, over the long term, prices or returns on financial assets tend to return to their historical average. This means that when an asset moves significantly away from its average, it is more likely to return to that average in the future. This idea is often used in trading and investment strategies such as pair trading and contrarian strategies.

These concepts can be considered to reflect universal laws observed in nature, especially with respect to the regularity of trends and cycles. For example, in nature, many phenomena follow regular cycles or average trends, such as seasons, plant growth cycles, or even the movements of planets.

However, it is important to note that financial markets are also influenced by numerous other factors, such as investor psychology, economic and political events, technological innovations, etc. Therefore, while drifting and averaging are important concepts, they do not capture the total complexity of financial markets.

Ultimately, in order to understand and succeed in financial markets, it is crucial to take into account a multitude of factors and concepts, in addition to drifting and averaging, and to adapt your strategies according to market conditions and investment goals.

9. Volume Profile and Footprints interests?

Volume Profiles and Footprints are two market analysis tools that are widely used by traders to assess price behavior and market sentiment based on trading volume. Here is an overview of each of these concepts:

1. Volume Profile: The Volume Profile, or Volume Profile, is a graphical tool that represents the distribution of trading volume at various price levels over a given period of time. It is often represented as a histogram or cloud chart, where each bar or area represents the quantity of volume traded at a specific price level. By analyzing the volume profile, traders can identify price levels where there has been the most trading activity, which can provide information about support and resistance levels, as well as areas of interest for buyers and sellers.
2. Footprints: Footprints are a type of market analysis tool that allows traders to visualize in detail the individual trades that took place at each price level. Footprints provide a granular view of trader behavior by showing buying (asking) and selling (offering) at specific price levels. By observing “Footprints,” traders can identify areas where there has been significant trading activity, as well as changes in market sentiment and buying or selling pressures.

By combining Volume Profiles and Footprints, traders can gain a better understanding of market behavior and identify potential trading opportunities. For example, a strong accumulation of volume at a particular price level on the Volume Profile, combined with “Footprints” showing strong buying activity at that level, could indicate a strong level of support where traders could consider entering a long position. Likewise, a strong accumulation of volume at a price level with “Footprints” showing strong selling activity could indicate potential resistance where traders could consider taking short positions.

In summary, Volume Profiles and Footprints are powerful market analysis tools that help traders visualize and interpret market behavior based on trading volume. By using them effectively, traders can make more informed decisions and improve their trading performance.

10. Is demography (population growth) ultimately the most important long-term indicator for global investment?

Yes of course! The concept of supply and demand remains the most important in the markets.

11. Trading on Wall Street with only a school certificate (first half of the 20th century) vs trading with a doctorate (evolution of strategies that work or not): Price action vs hypermathematization.

The evolution of trading on Wall Street from the beginning of the 20th century to the present day has been marked by significant changes in traders' skills, strategies, and educational requirements. Here is an overview of the evolution of these two approaches:

Trader with only a school certificate (first half of the 20th century):

• At a time when computer science and sophisticated mathematical models were not widely available, trading was based more on experience, intuition, and practical market knowledge.
• Traders often relied on price action, reading quote bands, and basic technical analysis to make trading decisions.
• Trading skills, speed of reaction, and the ability to interpret market information were key elements in the success of traders of this era.

Trader with a doctorate (recent evolution):

• With the advent of computing and advanced mathematical modeling, trading on Wall Street has seen a significant evolution towards more quantitative and algorithmic approaches.
• Traders with a doctorate in mathematics, quantitative finance, or related fields are increasingly in demand to develop and implement algorithmic trading strategies based on complex mathematical models.
• These traders often use techniques such as quantitative analysis, machine learning, advanced statistical models, and high-frequency trading algorithms to identify trading opportunities and execute trades at high speed.

The move towards more quantitative and mathematical strategies has been driven by several factors, including the increasing availability of market data, improved computing capabilities, and the goal of reducing transaction costs while maximizing returns. However, this does not mean that the price action approach has completely disappeared. Many traders continue to use technical analysis techniques and discretionary strategies based on observing price movements.

In summary, while traders in the first half of the 20th century focused primarily on experience and intuition, the recent evolution of trading on Wall Street saw the emergence of highly skilled traders with advanced mathematical skills and computer expertise, who exploit sophisticated quantitative models to make trading decisions.

To watch the interview on YouTube: https://www.youtube.com/live/hs32MFkVPZ8?si=w4VSP1O9KZtV-WqD

Find us on Génius Station: https://app.genius-station.com

‍