Extending our prior work on NLP Sentiment Scores with our thematic identification framework SmartBuzz, we develop trading signals based on machine identified short-term thematics found in the stock news articles and company earnings result transcripts for ASX 200 stocks.
We build SmartBuzz factors for various trading focused thematics on topics such as Earnings & Profits, Dividends, and ESG – testing for short-term moves in stock price after the results call and news publication. We use SmartBuzz to track the emergence and persistence of these themes through time, noting an increase in sentiment towards Earnings and Dividends Thematics recently.
What we find is that these text sources offers unique insights, information frequencies, timeliness, and challenges. We can exploit the text to trade longshort for up to 10 days after publication with an average return spread of up to 1% and more with combinations of signals and filters.
Identifying certain peculiarities with sentiment scores between both text sources, we find that using just the ‘Pos’ or ‘Neg’ labels works well for News, but for Transcripts we find a distinct bias that needs to be neutralised.
Relevance also proves to be a useful tool to filter some results.
Using a SmartBuzz factor built around ‘Reporting’ theme terms we tested the 10-day performance around the event dates. We found the original source of the event (i.e. the company transcripts) holds the strongest alpha, while News articles are useful with relevance filters.
Despite the biased ‘positive outlook’ found in management earnings calls, the SmartBuzz ‘Reporting’ factor is still effective at distinguishing between subsequent outperformers and underperformers as shown in Figure 1.
相关报告
哈佛1.6万字最新报告:中美AI霸权之争:鹿死谁手?(中英对照)
1.9w+
类型:专题
上传时间:2020-08
标签:中美、AI、人工智能)
语言:中英
金额:10元
哈尔滨工业大学:ChatGPT调研报告
1.7w+
类型:专题
上传时间:2023-03
标签:ChatGPT、OpenAI、人工智能)
语言:中文
金额:5积分
1200页2020北京智源大会文集:AI 下一个十年
1.4w+
类型:科技
上传时间:2020-11
标签:AI、人工智能、芯片)
语言:中文
金额:免费
清华-人工智能发展报告(2011-2020)
1.3w+
类型:行研
上传时间:2021-01
标签:人工智能、发展)
语言:中文
金额:5积分
深度研究:中美人工智能之比较分析
9546
类型:经管职场
上传时间:2021-08
标签:中美、人工智能、科技)
语言:中文
金额:免费
177页AI 全景报告 2020(英)
8493
类型:行研
上传时间:2020-10
标签:AI、人工智能)
语言:英文
金额:5积分
顶级投行万字报告:人工智能对经济增长的潜在巨大影响(中英对照)
7753
类型:宏观
上传时间:2023-04
标签:人工智能、经济增长、就业)
语言:中英
金额:3元
《AI未来》读书笔记
6995
类型:读书笔记
上传时间:2021-09
标签:人工智能、AI)
语言:中文
金额:9.9元
从CHAT_GPT到生成式AI(Generative AI):人工智能新范式,重新定义生产力
6815
类型:行研
上传时间:2023-01
标签:人工智能、生成式AI)
语言:中文
金额:5积分
《汽车企业数字化转型:认知与实现》读书笔记
6693
类型:读书笔记
上传时间:2022-01
标签:数字化转型、汽车、大数据)
语言:中文
金额:9.9元
积分充值
30积分
6.00元
90积分
18.00元
150+8积分
30.00元
340+20积分
68.00元
640+50积分
128.00元
990+70积分
198.00元
1640+140积分
328.00元
微信支付
余额支付
积分充值
应付金额:
0 元
请登录,再发表你的看法
登录/注册