386 lines
14 KiB
Markdown
386 lines
14 KiB
Markdown
|
||
|
||
|
||
#### Abu seeks the intelligent-strategy which be able to explained by of a word.
|
||
|
||
Abu can help users to improve the strategy automatically, take the initiative to analyze the behavior of the orders generated by the strategy to prevent the losing-money transaction.
|
||
|
||
Right now, we still writting code by hand, abu is designed to be running complete-automatically in the future, including the entire work-process and strategy itself.
|
||
|
||
Our expectations : abu users only need to provide some seed strategy, on the basis of these seeds, computer continue to self-learning, self-growth, to build a new strategy which can adjust its parameters with the time series data.
|
||
|
||
|
||
### 🏆 [WEB: https://www.abuquant.com](https://www.abuquant.com)
|
||
|
||
1. 🇨🇳 [CN symbol list:](https://www.abuquant.com/cn1/cn_symbol_list.html)
|
||
|
||
* 🇨🇳 [sh000001 week report:](https://www.abuquant.com/abu_context/output_cn_week1/report/sh000001/index.html)
|
||
* 🇨🇳 [sh000001 day report:](https://www.abuquant.com/abu_context/output_cn_day1/report/sh000001/index.html)
|
||
|
||
|
||
2. 🇺🇸 [US symbol list:](https://www.abuquant.com/us1/us_symbol_list.html)
|
||
|
||
* 🇺🇸 [usBABA week report:](https://www.abuquant.com/abu_context/output_us_week1/report/usBABA/index.html)
|
||
|
||
3. 🚩 [HK symbol list:](https://www.abuquant.com/hk1/hk_symbol_list.html)
|
||
* 🚩 [hk01810 week report:](https://www.abuquant.com/abu_context/output_hk_week1/report/hk01810/index.html)
|
||
|
||
4. 📡 [https://www.abuquant.com/find_itl.html](https://www.abuquant.com/find_itl.html)
|
||
|
||
* 📐 [Upward triangle consolidation and upward breakthrough:](https://www.abuquant.com/itl_feature1/pattern_90triangle_up_up_break_symbol_list.html)
|
||
* 🌊 [Wave theory retraces wave c point:](https://www.abuquant.com/itl_feature1/dn_5wr_c_revert_symbol_list.html)
|
||
|
||
* ✂️ [Risk of upward trend and downward breakthrough:](https://www.abuquant.com/itl_feature1/trend_breakthrough_risk_symbol_list.html)
|
||
|
||
* 🐶 [Point C will rise to point D to complete the downgrade of Saifu:](https://www.abuquant.com/itl_feature1/dn_cypher_xabc_predict_symbol_list.html)
|
||
* ☯ [Entangled discussion relay ❸ Buy up:](https://www.abuquant.com/itl_feature1/dn_right_tangle_three_symbol_list.html)
|
||
|
||
|
||
* 🚩[Wedge shaped sorting and upward breakthrough:](https://www.abuquant.com/itl_feature1/pattern_wedge_dn_break_symbol_list.html)
|
||
* 🦇[Bats have reached the point of ascending bats:](https://www.abuquant.com/itl_feature1/up_bat_abcd_regular_symbol_list.html)
|
||
|
||
* ☯️[Entangled discussion relay ❷ Buy up:](https://www.abuquant.com/itl_feature1/dn_right_tangle_two_symbol_list.html)
|
||
|
||
* 🌊[Wave Theory: Reversal of Waves:](https://www.abuquant.com/itl_feature1/up_5wr_c_revert_symbol_list.html)
|
||
|
||
* ⚔️[Trend line breakthrough opportunity:](https://www.abuquant.com/itl_feature1/trend_breakthrough_chance_symbol_list.html)
|
||
|
||
|
||
|
||
* ☯️[Entangled discussion relay ❸ Selling downwards:](https://www.abuquant.com/itl_feature1/up_right_tangle_three_symbol_list.html)
|
||
|
||
* 🐶[The completion of the D-point of the descending Saifu:](https://www.abuquant.com/itl_feature1/dn_cypher_xabc_predict_symbol_list.html)
|
||
|
||
* ▴▲▴[Head, shoulders, top down breakthrough:](https://www.abuquant.com/itl_feature1/trend_support_encounter_dn_symbol_list.html)
|
||
* ✂️[Strong upward trend, strong support, and possible breakout:](https://www.abuquant.com/itl_feature1/pattern_head_top_break_symbol_list.html)
|
||
|
||
* 🌊[Upward pullback wave relay b:](https://www.abuquant.com/itl_feature1/dn_5wr_b_pos_symbol_list.html)
|
||
|
||
* 🦊[Complete the reduction of Gali d point:](https://www.abuquant.com/itl_feature1/dn_gartley_abcd_predict_symbol_list.html)
|
||
|
||
* ☯️[Entangled discussion relay ❷ Sell downwards:](https://www.abuquant.com/itl_feature1/up_right_tangle_two_symbol_list.html)
|
||
* ✂️[Strong upward trend, strong support, and possible breakout:](https://www.abuquant.com/itl_feature1/pattern_head_top_break_symbol_list.html)
|
||
|
||
* ❐[Falling rectangle achieves the falling target:](https://www.abuquant.com/itl_feature1/pattern_rect_dn_up_target_symbol_list.html)
|
||
|
||
* 🌊[Wave theory falling relay c:](https://www.abuquant.com/itl_feature1/up_5wr_c_regular_symbol_list.html)
|
||
|
||
|
||
* 🦀️[The crab's D point has been completed:](https://www.abuquant.com/itl_feature1/up_crab_abcd_predict_symbol_list.html)
|
||
* ⚑[Flag lowering, sorting and upward breakthrough:](https://www.abuquant.com/itl_feature1/pattern_flag_dn_break_symbol_list.html)
|
||
|
||
* ☯[Entanglement reversal ❶ Buy up:](https://www.abuquant.com/itl_feature1/dn_lr_tg_one_symbol_list.html)
|
||
|
||
* 🌊[Wave theory rising relay c:](https://www.abuquant.com/itl_feature1/dn_5wr_c_regular_symbol_list.html)
|
||
|
||
|
||
* 🦇[Rising Bat 3rd Rebound Target:](https://www.abuquant.com/itl_feature1/up_bat_hm_t3_symbol_list.html)
|
||
* 🚩[Rising wedge type achieves the goal of consolidation and decline:](https://www.abuquant.com/itl_feature1/pattern_wedge_up_target_symbol_list.html)
|
||
|
||
* ☯[The entanglement center B has just been completed:](https://www.abuquant.com/itl_feature1/up_left_ds_large_tg_one_symbol_list.html)
|
||
|
||
|
||
5. 🅚[K-line composite signal strategy:](https://www.abuquant.com/find_kc.html)
|
||
|
||
|
||
* [Upward Pinbar Combination:](https://www.abuquant.com/kc_feature1/up_pinbar_symbol_list.html)
|
||
* [downpour:](https://www.abuquant.com/kc_feature1/dn_down_pour_symbol_list.html)
|
||
* [Low end Wuyang Line:](https://www.abuquant.com/kc_feature1/up_lp_5yang_symbol_list.html)
|
||
|
||
* [Rising and carrying six:](https://www.abuquant.com/kc_feature1/up_pregnant_6m_symbol_list.html)
|
||
* [key stand:](https://www.abuquant.com/kc_feature1/up_1needle_symbol_list.html)
|
||
|
||
### Index
|
||
|
||
| Content | Path |
|
||
| ------| ------ |
|
||
| Abu Quantitative Trading System | ./abupy |
|
||
| Abu Quantitative Trading Tutorial | ./abupy_lecture |
|
||
| 《量化交易之路》 (The Road of Quantitative Trading) example code | ./ipython and ./python|
|
||
| 《机器学习之路》 (The Road of Machine Learning) example code | https://github.com/maxmon/abu_ml |
|
||
|
||
### Feature
|
||
|
||
* Optimizing strategies by a variety of machine learning techniques
|
||
* Guiding traders in real trading, improving the profit of strategy, to beat the market
|
||
|
||
### Supported investment markets:
|
||
|
||
* US stocks, A stocks, Hong Kong stocks
|
||
* Futures market, Options Market
|
||
* BTC(bitcoin)，LTC(Litecoin)
|
||
|
||
### Project Design Goal：
|
||
|
||
* Separate basic strategy and strategy optimization module
|
||
* Improve flexibility and adaptability
|
||
|
||
## Install
|
||
|
||
### Deploy
|
||
|
||
Recommended to use Anaconda to deploy the Python environment, see [here](http://www.abuquant.com/lecture/lecture_0.html)
|
||
|
||
### Test
|
||
|
||
```python
|
||
import abupy
|
||
```
|
||
|
||
## UI operation（Non programming）
|
||
|
||
|
||
|
||
[More examples of UI operations](./abupy_ui/readme.md)
|
||
|
||
## Document
|
||
|
||
### 1: Develop Trading Strategy
|
||
|
||
[Section 1 UI operation tutorial](https://v.qq.com/x/page/g0555b9k6ge.html)
|
||
|
||
Trading strategy decide when to invest, backtesting tell us the simulation of profit about this strategy in the historical data.
|
||
|
||
1. coding buy factor
|
||
2. backtesting factor step by step
|
||
3. coding sell factor
|
||
|
||
[see more](http://www.abuquant.com/lecture/lecture_1.html)
|
||
|
||
### 2: Optimize Trading Strategy
|
||
|
||
Through stop loss and profit cap to keep profit generated by the strategy, lower risk.
|
||
|
||
1. basic stop loss and profit cap strategy
|
||
2. stop loss strategy
|
||
3. profit cap strategy
|
||
|
||
|
||
|
||
[see more](http://www.abuquant.com/lecture/lecture_2.html)
|
||
|
||
### 3: Slippage and Transaction Costs
|
||
|
||
Consider slippage and transaction costs on applying the strategy
|
||
|
||
1. implement slippage strategy
|
||
2. custom transaction costs
|
||
|
||
| type | date | symbol | commission |
|
||
| ------| ------ | ------ | ------ |
|
||
| buy | 20150423 | usTSLA | 8.22 |
|
||
| buy | 20150428 | usTSLA | 7.53 |
|
||
| sell | 20150622 | usTSLA | 8.22 |
|
||
| buy | 20150624 | usTSLA | 7.53 |
|
||
| sell | 20150706 | usTSLA | 7.53 |
|
||
| sell | 20150708 | usTSLA | 7.53 |
|
||
| buy | 20151230 | usTSLA | 7.22 |
|
||
| sell | 20160105 | usTSLA | 7.22 |
|
||
| buy | 20160315 | usTSLA | 5.57 |
|
||
| sell | 20160429 | usTSLA | 5.57 |
|
||
|
||
[see more](http://www.abuquant.com/lecture/lecture_3.html)
|
||
|
||
### 4: Multi-stock Backtesting and Position Control
|
||
|
||
Backtesting on multiple stocks, control position to lower risk.
|
||
|
||
1. multiple stocks with same factor
|
||
2. custom position-control strategy
|
||
3. multiple stocks with different factor
|
||
4. faster running with multi-processing
|
||
|
||
|
||
|
||
[see more](http://www.abuquant.com/lecture/lecture_4.html)
|
||
|
||
### 5: Develop Stock-picking Strategy
|
||
|
||
A good trading strategy needs a good stock.
|
||
|
||
1. coding stock-picking factor
|
||
2. run multiple stock-picking factor
|
||
3. faster running with multi-processing
|
||
|
||
[see more](http://www.abuquant.com/lecture/lecture_5.html)
|
||
|
||
### 6: Metrics on Backtesting
|
||
|
||
Good metric give you right direction.
|
||
|
||
1. basic useage about metric
|
||
2. visualization on metrics
|
||
3. expand self-custom metric
|
||
|
||
|
||
[see more](http://www.abuquant.com/lecture/lecture_6.html)
|
||
|
||
### 7: Seeking the best parameter for Strategy and Scoring
|
||
|
||
By customizable scoring, seek the best parameter for strategy.Like:how many days should be on MA?
|
||
|
||
1. parameter range
|
||
2. using grid search to seek the best parameter
|
||
3. metric on scoring
|
||
4. scoring with different weight
|
||
5. custom scoring by yourself
|
||
|
||
[see more](http://www.abuquant.com/lecture/lecture_7.html)
|
||
|
||
### 8: Backtesting on A-Stock
|
||
|
||
1. backtesting on A-Stock example
|
||
2. dealing with price limit
|
||
3. analyze multiple trading result
|
||
|
||
[see more](http://www.abuquant.com/lecture/lecture_8.html)
|
||
|
||
### 9: Backtesting on HK-Stock
|
||
|
||
1. backtesting on HK-Stock example
|
||
2. optimize strategy, improve the stability of the system
|
||
3. encapsulate the "strategy" of optimizing the strategy as a class decorator
|
||
|
||
|
||
|
||
|
||
[see more](http://www.abuquant.com/lecture/lecture_9.html)
|
||
|
||
### 10: Backtesting on Bitcoin and LiteCoin
|
||
|
||
1. analyze bitcoin and litecoin market trend
|
||
2. visualization analysis on bitcoin and litecoin market trend
|
||
3. backtesting on Bitcoin and LiteCoin market
|
||
|
||
* bitcoin loss10: [-26.895, -3.284] , top10：(4.182, 38.786]
|
||
* bitcoin recent 1 year risk lower：loss10: [-16.273, -2.783], top10: (3.948, 15.22]
|
||
* litecoin loss10: [-28.48, -4.1]， top10: (4.405, 41.083]
|
||
* litecoin recent 1 year risk lowerloss10: [-22.823, -3.229] 高收益top10: (5.0606, 37.505]
|
||
|
||
[see more](http://www.abuquant.com/lecture/lecture_10.html)
|
||
|
||
### 11: Backtesting on Futures Market
|
||
|
||
1. features of futures market
|
||
2. backtest bullish contract
|
||
3. backtest bearish contract
|
||
4. optimize strategy by displacement ratio
|
||
|
||
[see more](http://www.abuquant.com/lecture/lecture_11.html)
|
||
|
||
### 12: Bitcoin with Machine Learning Example
|
||
|
||
How to use machine learning technology correctly in quantitative trading of investment goods?
|
||
|
||
1. extraction of bitcoin features
|
||
2. abu built-in machine learning module
|
||
3. verification and unbalanced technology of test set
|
||
4. inherits AbuMLPd to encapsulate data processing
|
||
|
||
[see more](http://www.abuquant.com/lecture/lecture_12.html)
|
||
|
||
### 13: Quantitative Technology Analysis and Applications
|
||
|
||
Technical analysis is based on three assumptions:1. The market discounts everything.2. Price moves in trends.3. History tends to repeat itself.
|
||
|
||
1. resistance line, support line automatically drawn
|
||
2. analysis of gap
|
||
3. analysis of traditional technical metric
|
||
|
||
[see more](http://www.abuquant.com/lecture/lecture_13.html)
|
||
|
||
### 14: Quantitative Correlation Analysis Application
|
||
|
||
Behind similar investment trend, it is often with similar investment groups.
|
||
|
||
1. relevant similarity measure
|
||
2. distance measurement and similarity
|
||
3. application of similarity interface
|
||
4. natural correlation
|
||
|
||
[see more](http://www.abuquant.com/lecture/lecture_14.html)
|
||
|
||
### 15: Quantitative Trading and Search Engines
|
||
|
||
Search and analyze failed orders generated by strategy, intercept possible failing orders by the ump .
|
||
|
||
1. backtest splitted set
|
||
2. analyze transaction manually
|
||
3. concept of referee system
|
||
4. angle referee
|
||
5. give a natural and reasonable explanation
|
||
6. optimal classification-cluster selection
|
||
|
||
|
||
|
||
[see more](http://www.abuquant.com/lecture/lecture_15.html)
|
||
|
||
### 16: UMP Main Referee System
|
||
|
||
|
||
1. gap main-referee
|
||
2. price main-referee
|
||
3. fluctuation main-referee
|
||
4. verify whether the main-referee works well
|
||
5. organize referees to make more complex comprehensive decisions
|
||
6. let the referee learn how to cooperate with their own to make the most correct judgments
|
||
|
||
|
||
[see more](http://www.abuquant.com/lecture/lecture_16.html)
|
||
|
||
### 17: UMP Edge Referee System
|
||
|
||
1. gap edge-referee
|
||
2. price edge-referee
|
||
3. fluctuation edge-referee
|
||
4. comprehensive edge-referee
|
||
5. verify whether the edge-referee works well
|
||
6. open the edge-referee mode
|
||
|
||
[see more](http://www.abuquant.com/lecture/lecture_17.html)
|
||
|
||
### 18: Custom Referee System
|
||
|
||
1. train new main-referee from different perspectives
|
||
2. train new edge-referee from different perspectives
|
||
3. add a new perspective to record the game (record backtesting feature)
|
||
4. main-referee with the new perspective
|
||
5. edge-referee with the new perspective
|
||
|
||
The design goals of ump module are:
|
||
|
||
* no need to hard-code strategy
|
||
* mo need to manually set the threshold
|
||
* separate the strategy and optimize-monitor module to improve flexibility and adaptability
|
||
* discover issues hidden in strategy
|
||
* auto-learn new transaction data
|
||
|
||
[see more](http://www.abuquant.com/lecture/lecture_18.html)
|
||
|
||
### 19: Data Source
|
||
|
||
Abu support stock, futures, digital coins and other financial investment. Abu support quotes query and transactions, and also offer a high degree of customization.
|
||
|
||
|
||
1. switch data mode
|
||
2. switch data storage
|
||
3. switch data source
|
||
4. update the whole market data
|
||
5. access to external data sources：stock data sources
|
||
6. access to external data sources：futures data sources
|
||
7. access to external data sources：bitcoin and litecoin data sources
|
||
|
||
[see more](http://www.abuquant.com/lecture/lecture_19.html)
|
||
|
||
## Contact us
|
||
|
||
More abu quantitative tutorial please pay attention to our WeChat public number: abu_quant
|
||
|
||
Also any questions, please contact my personal WeChat number:
|
||
|
||
|
||
|
||
### License
|
||
|
||
[GPL](./LICENSE)
|