Traditional machine learning classification model predicts the rise and fall of stock prices

Preface

The stock market is surging , Only a good forecast of the stock price can we better seize the profit opportunity . So what is the effect of the traditional machine learning classification model in this respect ？
This paper only considers 5、10、20 Daily moving average 、 Moving exponential average In the case of these six indicators , Comparison of the Support vector machine 、 Decision tree 、 Random forests Three models predict the effect of stock price fluctuation

Generally speaking, the more technical indicators , It can also be combined with screening effective indicators before bringing them into the prediction model

disclaimer

Nothing in this vision and analysis should be interpreted as investment advice , Past performance does not necessarily indicate future results .

---

We choose Maotai stock (600519) As an object of study , The data date range is 2020-01-01 To 2020-12-30. Uniform adoption of the last 64 Day data as test set , Last 64 The data of days ago is used as the training set

---

Support vector machine

Support vector machine （SVM） It is a kind of generalized linear classifier which classifies data according to supervised learning , The decision boundary is the maximum margin hyperplane for learning samples

In order to increase the nonlinearity of the model , use RBF Kernel function , The effect of the model is as follows
only 42.47% The accuracy of

The accuracy is too low , The prediction is not accurate

---

Decision tree

Decision tree (Decision Tree） On the basis of knowing the probability of occurrence of various situations , The probability that the expected value of NPV is greater than or equal to zero is calculated by constructing decision tree , Evaluate project risks , The decision analysis method to judge its feasibility , It is a graphic method of intuitively using probability analysis . Because this kind of decision branch is like a tree's branch , So it's called decision tree . In machine learning , Decision tree is a prediction model , It represents a mapping relationship between object attributes and object values

The depth of the defined number is 5, The effect of the model is as follows
The accuracy on the training set is 77.53%, The accuracy on the test set is 56.25%, Compared with the support vector machine model, it has a certain improvement , But there are still big problems

Although the accuracy has been improved, the prediction effect is still not good , And observe the output prediction results , Most of the time, it is predicted that it will fall , It shows that the classification effect is not very good

---

Random forests

Random forest is a classifier that contains multiple decision trees , And the output category is determined by the mode of the output category of the individual tree

Define the depth of the tree as 5, The number of random trees is 10, The effect of the model is as follows
The accuracy on the training set is 86.52%, The accuracy on the test set is 57.81%, The result of prediction is better than that of decision tree

Slightly improved accuracy , The increase of recall rate is relatively large , But there is still much room for improvement

---

summary

After a simple test , The effect of random forest is relatively optimal

The main reason why the accuracy rate is low is that there are too few selected indicators , Want to know how many indicators are needed 、 Which indicators are more reliable are more helpful to the model , Further research is needed