Alternative Data News | Neudata

Comprehending machine learning explainability: deep neural networks and automated trading

We summarise a recent paper based on a high-frequency trading firm that adopts deep neural network (DNN) machine learning systems for trading functions. The paper considers how we can begin to explain the decisions of DNNs, despite their opacity.

New Literature Review 9 Aug 2022
Inflation studies – anticipating official CPI figures with alternative data

With current concerns over rising inflation across major economies, we summarise two studies that anticipate official CPI figures ahead of their release. These studies use high-frequency alternative data sources, which are found to improve the forecast accuracy of inflation models and provide timely insights into global pricing dynamics.

Literature Review 26 Jul 2022
Developing a Japanese alternative data consumption index

Recent research from 2022 suggests that incorporating transactional and POS data can replicate or outperform the Bank of Japan’s current Consumption Activity Index released since 2016. We summarise the findings of this research and highlight several Neudata-listed data providers that may be leveraged for such use cases.

Literature Review 11 Jul 2022
Machine learning and the Chinese stock market

We summarise the key findings from a recent research paper that examines the features of the Chinese stock market through various machine learning models and analyses the predictability of different machine learning models for Chinese stock returns.

Literature Review 1 Jul 2022
Consumer behaviour data and portfolio performance

We summarise a paper that questions if various sources of ‘consumer big data’ can predict company revenue and stock returns. We highlight several Neudata-listed clickstream, geolocation and brand sentiment providers that may be applicable for this use case.

Literature Review 15 Jun 2022
Systematic trading strategies built on machine-readable news

We summarise a research paper which showcases how equity investors can use machine-readable news data to create systematic trading strategies. The researcher was able to do so by deriving sentiment indicators from a large point-in-time dataset of news articles.

Literature Review 31 May 2022
ESG credit ratings and the Big Three

A 2021 paper analysed how Moody’s, S&P, and Fitch, integrate ESG into their sovereign credit ratings. We add to the research’s demarcation between the three methodologies and highlight alternative ESG credit rating providers

Literature Review 17 May 2022
What is the price of data?

A trio of academics recently surveyed the dataset catalogues of nearly 40 commercial data marketplaces to empirically answer the question: what is the price of data? We summarise key findings from this study, such as median price of a dataset, as well as compare the literature’s conclusions with Neudata’s own metadata.

Literature Review 4 May 2022
Nowcasting Japan’s GDP using alternative data

Recent research from 2022 suggests that incorporating POS and Google Trends data can improve the precision and accuracy of Japanese GDP nowcasts. We summarise these findings and highlight several Neudata-listed data providers that may be leveraged for such use cases.

Literature Review 19 Apr 2022
What are the best factors to consider when pricing crypto assets?

We summarise a 2022 working paper that developed a new five-factor model to better price and classify major cryptocurrencies.

Literature Review 5 Apr 2022

Follow us