Analytics News and Market Forecast

Gold remains a US interest rate play for now with rising US Treasury yields sending the precious metal lower after a robust US Jobs Report. The weekly price is on ranging near and around 200 SMA for the bearish trend to be reversed if the price breaks Fibo support level at 1614 to below or for the bullish trend to be resumed in case of the price breaks resistance level at 1788 to above.

more...

Gold and silver have both benefitted from a weaker dollar but silver is the standout of the two metals. Gold consolidating at stern resistance, silver continues higher

more...

Dollar Index rallied higher this week as Fed hawks and US data put the Dollar back on top. Can the rally continue?

more...

EUR/USD will be dancing to the US dollar’s tune next week with Fed chair Powell’s Semi-Annual Testimony to the US Senate’s Banking Committee and the delayed US Jobs Report the highlights.

more...

Currently, there are a huge number of trading strategies for every taste. All these strategies are aimed at making a profit. But making a profit is in one way or another connected with the risks - the greater the expected profit, the higher the risks. A logical question arises: is it possible to reduce trading risks to a minimum, while receiving small but stable profits? These conditions are met by pair trading.

Pair trading is a variery of statistical arbitrage first proposed by Jerry Bamberger in the 1980s. This trading strategy is market neutral, allowing traders to profit in almost any market condition. Pair trading is based on the assumption that the characteristics of interrelated financial instruments will return to their historical averages after a temporary deviation.

more...

Money is flowing into small caps, growth stocks, and gold – is this a bullish or bearish sign? And, what does a one-day pop indicate with regard to trend direction?

more...

Long Short-Term Memory(LSTM), is a type of recurrent neural network designed for sequence tasks, excelling in capturing and utilizing long-term dependencies in data. Unlike vanilla Recurrent Neural Networks(simple RNNs) discussed in the previous article of this series (a must-read). Which can't capture long-term dependencies in the data.

more...

Convolutional Neural Networks (CNNs) are a class of deep learning algorithms specifically designed to process structured grid-like data, such as images, audio spectrograms, and time-series data. They are particularly well-suited for visual data tasks because they can automatically and adaptively learn spatial hierarchies of features from input data.

more...

Machine learning models are very sensitive instruments. In this series of articles, we will pay significantly more attention to how the transformations we apply to our data, affects our model's performance. Likewise, our models are also sensitive to how the relationship between the input and the target is conveyed. This means, we may need to create new features from the data we have at hand, in order for our model to effectively learn.

more...

We continue our series on the MQL5 wizard, where lately we are alternating between simple patterns from common indicators and reinforcement learning algorithms. Having considered indicator patterns (Bill Williams’ Alligator) in the last article, we now return to reinforcement learning, where this time the algorithm we are looking at is Proximal Policy Optimization (PPO). It is reported that this algorithm, that was first published 7 years ago, is the reinforcement-learning algorithm of choice for ChatGPT. So, clearly there is some hype surrounding this approach to reinforcement learning. The PPO algorithm is intent on optimizing the policy (the function defining the actor’s actions) in a way that improves overall performance by preventing drastic changes that could make the learning process unstable.

more...