Kun Li / Profile
![Kun Li](https://c.mql5.com/avatar/avatar_na2.png)
![JC](https://c.mql5.com/avatar/avatar_na2_micro.png)
![Kun Li](https://c.mql5.com/avatar/avatar_na2.png)
![How to use ONNX models in MQL5](https://c.mql5.com/2/52/onnx_models_avatar.png)
ONNX (Open Neural Network Exchange) is an open format built to represent machine learning models. In this article, we will consider how to create a CNN-LSTM model to forecast financial timeseries. We will also show how to use the created ONNX model in an MQL5 Expert Advisor.
![Kun Li](https://c.mql5.com/avatar/avatar_na2.png)
![Kun Li](https://c.mql5.com/avatar/avatar_na2.png)
![Kun Li](https://c.mql5.com/avatar/avatar_na2.png)
![Kun Li](https://c.mql5.com/avatar/avatar_na2.png)
![Kun Li](https://c.mql5.com/avatar/avatar_na2.png)
![Kun Li](https://c.mql5.com/avatar/avatar_na2.png)
![Data Science and Machine Learning (Part 02): Logistic Regression](https://c.mql5.com/2/48/logistic_regression__1.png)
Data Classification is a crucial thing for an algo trader and a programmer. In this article, we are going to focus on one of classification logistic algorithms that can probability help us identify the Yes's or No's, the Ups and Downs, Buys and Sells.
![Kun Li](https://c.mql5.com/avatar/avatar_na2.png)
![Population optimization algorithms: Cuckoo Optimization Algorithm (COA)](https://c.mql5.com/2/50/Cuckoo-Optimization-Algorithm-avatar.png)
The next algorithm I will consider is cuckoo search optimization using Levy flights. This is one of the latest optimization algorithms and a new leader in the leaderboard.
![Kun Li](https://c.mql5.com/avatar/avatar_na2.png)
![Population optimization algorithms: Grey Wolf Optimizer (GWO)](https://c.mql5.com/2/50/grey_wolf_optimizer_avatar.png)
Let's consider one of the newest modern optimization algorithms - Grey Wolf Optimization. The original behavior on test functions makes this algorithm one of the most interesting among the ones considered earlier. This is one of the top algorithms for use in training neural networks, smooth functions with many variables.
![Kun Li](https://c.mql5.com/avatar/avatar_na2.png)
![MetaQuotes](https://c.mql5.com/avatar/2010/1/4B5DE8B4-9045.jpg)
![Kun Li](https://c.mql5.com/avatar/avatar_na2.png)
![Boris](https://c.mql5.com/avatar/2015/2/54E6173A-2577.jpg)
![Kun Li](https://c.mql5.com/avatar/avatar_na2.png)
![Population optimization algorithms: Artificial Bee Colony (ABC)](https://c.mql5.com/2/50/artificial_bee_colony_avatar.png)
In this article, we will study the algorithm of an artificial bee colony and supplement our knowledge with new principles of studying functional spaces. In this article, I will showcase my interpretation of the classic version of the algorithm.
![Kun Li](https://c.mql5.com/avatar/avatar_na2.png)
![Analysis of the Main Characteristics of Time Series](https://c.mql5.com/2/0/Time_Series_Analysis_in_MQL5.png)
This article introduces a class designed to give a quick preliminary estimate of characteristics of various time series. As this takes place, statistical parameters and autocorrelation function are estimated, a spectral estimation of time series is carried out and a histogram is built.
![Kun Li](https://c.mql5.com/avatar/avatar_na2.png)
![Kun Li](https://c.mql5.com/avatar/avatar_na2.png)
![Kun Li](https://c.mql5.com/avatar/avatar_na2.png)
![The Implementation of Automatic Analysis of the Elliott Waves in MQL5](https://c.mql5.com/2/0/MQL5_Elliott_Waves_Automated.png)
One of the most popular methods of market analysis is the Elliott Wave Principle. However, this process is quite complicated, which leads us to the use of additional tools. One of such instruments is the automatic marker. This article describes the creation of an automatic analyzer of Elliott Waves in MQL5 language.
![Kun Li](https://c.mql5.com/avatar/avatar_na2.png)
![The ZigZag Indicator: Fresh Approach and New Solutions](https://c.mql5.com/2/0/avatar2.png)
The article examines the possibility of creating an advanced ZigZag indicator. The idea of identifying nodes is based on the use of the Envelopes indicator. We assume that we can find a certain combination of input parameters for a series of Envelopes, whereby all ZigZag nodes lie within the confines of the Envelopes bands. Consequently, we can try to predict the coordinates of the new node.
![Kun Li](https://c.mql5.com/avatar/avatar_na2.png)
![Indicator for Renko charting](https://c.mql5.com/2/0/LOGO__2.png)
The article describes an example of Renko charting and its implementation in MQL5 as an indicator. Modifications of this indicator distinguish it from a classic chart. It can be constructed both in the indicator window and on the main chart. Moreover, there is the ZigZag indicator. You can find a few examples of the chart implementation.