Prediction of trend of Stock Price (of coming 7..10 days)

 Approach : Regression (predict change of status (Rise/Drop), with estimated range)

Steps of analysis       

1. Collect data, records of below fields of previous 30 days

[Features]

  • Max, Min, open, close
  • Status (Drop/Rise compared with previous date)
  • Number of successive days of drop or rise
  • Total # of lots of transaction (purchase, sold), total amount of transaction (purchase, sold). total # of transaction (purchase, sold, eg: 1 transaction may involve 20 logs of transaction)

 [Output, compared with previous day]

  •  Status (rise / drop)
  • % of change of stock price (rise / drop)

2.    Conduct correlation analysis of above fields

3.         Based on result of correlation analysis, select fields (features) for analysis

4.         Divide records into “Training Set” and “Test Set”

5.         By using Polynormal Regression, change degree, check accuracy à stop if overfit

6.         Test prediction upon data of tomorrow (status, and % of rise/drop)

7.         Repeat above, based on records of previous 60 days and 90 days

[Further estimation of next 7..10 days]

8.         Assume there are 4 features and 1 result, use result of prediction and 3 features to estimated value of the 4th feature. Use this approach to estimate values of all the 4 features of tomorrow.

9.     Based on estimated features of tomorrow, predict status (and % of drop/rise) of the day after tomorrow. Use this recursive approach to predict stock price of coming 7..10 days.

**Will be interesting to compare the prediction with actual trend of stock price for the coming 7..10 days.

Comments

Popular posts from this blog

自修溫習|港大醫科生研溫書App(筆記系統化助「主動回憶」)( 部份轉載)

Agent based intelligent KM (Knowledge Management) Chatbot (Part 1)