Why long samples are one of the keys to improving predictive algorithms in finance

In a study published in the KeAi The Journal of Finance and Data Science, Guillaume Coqueret, a Professor of Finance and Data Science at France’s EMLYON Business School, considered three dimensions of factor models based on ML: the persistence of the dependent variable, the size of the samples, and the holding period (i.e., the rebalancing frequency of the portfolio). His analysis focused on the US stock market.

A new cell factory for high-efficiency production of ectoine

A study published in the KeAi journal Green Chemical Engineering, has reported the biotechnological construction of an efficient ectoine cell factory based on E. coli BL21(DE3). Using metabolic engineering, researchers synthesised the ectoine with the E. coli, using glucose as the sole carbon source. By reconstructing the ectoine synthetic pathway, and enhancing the biosynthesis of ectoine precursor in E. coli, a high level of 60.7 g/L of ectoine was produced using a fed-batch fermentation approach.

Mapping the impact of tiered pricing reform on China’s residential electricity use

According to author Xiumei Yu: “The results of the paper have several policy implications. The fact that the average residential electricity use was reduced by the tiered pricing reform shows that this kind of reform can encourage residents to reduce their electricity use. In addition, our results suggest that policy intensity can be a powerful tool to guide residents to use electricity more efficiently.”

Take advantage of discounted APCs in open access week

KeAi is proud to be an open access publisher and as part of open access week we are delighted to offer our authors a heavily discounted or full waiver of article publishing charges (APC) for the majority of the journals we publish. To take advantage of this offer, submit your paper for consideration between 25 and 31 October, 2021.

New NLP model improves stock market predictions

A group of researchers at the Research Center for Social Computing and Information Retrieval at China’s Harbin Institute of Technology have constructed a model that can synthesise these multiple data sources and the various forms of data they contain. Study results, published in the KeAi journal AI Open, show that their model achieves a higher AUC (area under the precision-recall curve) score than existing models.

Scientists develop AI to predict the success of startup companies

In a bid to identify which companies are more likely to succeed, researchers have developed machine-learning models trained on the historical performance of over 1 million companies. Their results, published in KeAi’s The Journal of Finance and Data Science, show that these models can predict the outcome of a company with up to 90% accuracy. This means that potentially 9 out of 10 companies are correctly assessed.

Stay Informed

Register your interest and receive email alerts tailored to your needs. Sign up below.