Forecasting

The disagreement is an open area of research in an interdisciplinary field known as Explainable Artificial Intelligence (XAI). Explainable Artificial Intelligence attempts to help us understand how our models are arriving at their decisions but unfortunately everything is easier said than done.

We are all aware that machine learning models and available datasets are growing larger and more complex. As a matter of fact, the data scientists who develop machine learning algorithms cannot exactly explain their algorithm’s behaviour across all possible datasets. Explainable Artificial Intelligence (XAI) helps us build trust in our models, explain their functionality and validate that the models are ready to be deployed in production; but as promising as that may sound, this article will show the reader why we cannot blindly trust any explanation we may get from any application of Explainable Artificial Intelligence technology.

more...

Gold aka XAUUSD at present traded at 2158, I think 2150 is support zone for gold recently, despite prices break this level, eventually back above the price. Market today might waiting important news the FED rate decision, my forecast for gold in near future the price probably move higher above 2158 even back to high 2192.

This article is about the triangular arbitrage strategy, it has an example of two triangular arbitrages, and this is done with deep learning models, which are added to the downloads, and a EA which is also added to the downloads. Triangular arbitrage leverages discrepancies in exchange rates to generate risk-free profits.

more...

Gold prices are trying to hold above the $2,400 resistance, snapping a three-day corrective decline from record highs of $2,484. The price of gold is benefiting from a general weakening US dollar and low US Treasury yields, although markets remain risk-averse.

In this article, we closely examine the classic price action trading strategy of trading based on “higher highs” or “lower lows.” We trained various models to predict two distinct targets. The first target involved predicting changes in price, the simplest target possible. The second target aimed to determine whether the future close price would be higher than the current high, lower than the current low, or between the two.

more...

Forex forecasting by taking historical data of a trading instrument is interesting, programmers may easily be able to process price data to predict future prices, but I think fundamental factors can change forecasting accuracy.

We continue these series on the different ways key component classes of wizard assembled Expert Advisors can be implemented by considering 2 Gaussian Process Kernels. The linear-kernel and Matérn Kernel. The former is so simple you cannot find its Wikipedia-page, however the latter has a reference page over here.

There are several additional advantages and uses to GPs like noise handling & reduction as well as adaptation to regime change and many others. As traders, though, we want to capitalize on these benefits, so let’s look at a very basic linear kernel.

more...

Reinforcement Learning (RL) allows trading systems to learn from their environment or market data and thus improve their ability to trade over time. RL enables adaptation to changing market conditions, making it suitable for certain dynamic financial markets and securities. Financial markets are unpredictable, as often they feature a high degree of uncertainty. RL excels at making decisions under uncertainty by continuously adjusting its actions based on received feedback (rewards), thus being very helpful to traders when handling volatile market conditions.

more...

This article continues our look at reinforcement learning by considering another algorithm, namely the Monte-Carlo. This algorithm is very similar and in fact arguably encompasses both Q-Learning and SARSA in that it can be either on-policy or off-policy. What sets it apart though is the emphasis on episodes. These simply are a way of batching the reinforcement learning cycle updates, that we introduced in this article, such that the updating of the Q-Values of the Q-Map happens less frequently.
With the Monte Carlo algorithm, Q-Values are only updated after the completion of an episode. An episode is a batch of cycles. For this article, we have assigned this number of cycles the input parameter ‘m_episodes_size’ and it is optimizable or adjustable. Monte Carlo is attributed to being quite robust to market variability because it can better simulate a wide range of possible market scenarios, allowing traders to determine how different strategies perform under a variety of conditions. This variability helps traders understand potential tradeoffs, risks and returns, enabling them to make more informed decisions.

more...

The introduction to temporal difference (TD) learning in reinforcement learning serves as a gateway to understand how TD distinguishes itself from other algorithms, such as Monte Carlo, Q-Learning, and SARSA. This article aims to unravel the complexities surrounding TD learning by highlighting its unique ability to update value estimates incrementally based on partial information from episodes, rather than waiting for episodes to complete as seen in Monte Carlo methods. This distinction makes TD learning a powerful tool, especially where environments are dynamic and require prompt updates to the learning policy.

In the last reinforcement-learning article, we looked at the Monte Carlo algorithm that gathered reward information over multiple cycles before performing a single update for each episode. Temporal difference (TD) though, is all about learning from partial and incomplete episodes much like the algorithms of Q-Learning and SARSA that we tackled earlier on here and here.

more...