![]() ![]() I first started at NASA about five years ago with the task of examining knowledge management within the organization. It’s important not to try and fit your data into a visualization let your data drive how you visualize the information.īelow is a quick summary slide of what I just went over: ![]() When you combine the three, you end up with what I call data-driven visualization. Knowledge management is used for strategy, informatics provides the pipeline to create storage capabilities with applications to transmit data from where it’s stored to end users, and data science provides the algorithms and methodologies that allow you to convert that data into actionable knowledge for your end users. To convert data to knowledge, a convergence of knowledge management, informatics and data science is necessary. We have to try to break down those silos, which is exactly the capability that graph databases provide. And this volume of data keeps growing in terms of variety, velocity, volume, value and veracity.īut our biggest challenge is the accessibility of this information due to the silos between departments and also within our individual groups, products and programs. This data includes hundreds of millions of documents, reports, project data, lessons learned, scientific research, medical analysis and more stored in a nationwide database. How do we do that?įirst let’s go over some of the challenges your organization will likely have to overcome.Īt NASA we have around 18 to 20 different locations with a total of 80,000 employees, and have been collecting data since the late 1950s/early 1960s. This makes it more important than ever to increase the productivity of our knowledge worker. By the time I finish this presentation, I hope you’ll see why knowledge architecture is important and have a framework for taking it back to your organizations - managers, investors and funders - and show them how this can implemented within your organization.īack in 1999, Peter Drucker said, “The most important contribution management needs to make in the 21st century is to increase the productivity of knowledge work in the knowledge worker.” Since that time social media has exploded, the Internet of Things (IoT) has taken off and we constantly have more and more data available. Only 1 week loss in 13 weeks of running time.Knowledge architecture combines the different disciplines of knowledge management, informatics, and data science, which we use to extract knowledge from our “ Lessons Learned” database. With GALSTM model, the products managed by our fully automatic quantitative trading system achieved an absolute annual return rate of 44.71% and the standard deviation of daily returns is only 0.42% in three months of operation. We then construct a long and short positions combination, select long positions in the A shares of the entire market, and use stock index futures to short. The proposed GALSTM enables us to expand the scope of stock selection under the premise of controlling risks with limited hedging tools in the A-share market, thereby effectively increasing high-frequency excess returns. In addition, we also build matching data process plus portfolio management modules to form a complete system. Then an attention-based LSTM is built to learn the weighting matrix underlying the dynamic graph. This procedure provides a good training start as the multi-Hawkes Processes will be studied on the most saint feature fluctuations with any correlations being statistically significant. First, a multi-Hawkes Process is used to initial a correlation graph between stocks. In this paper, we propose a novel machine learning model named Graph Attention Long Short-Term Memory (GALSTM) to learn the correlations between stocks and predict their future prices automatically. Traditional methods only take some certain factors into consideration but ignore others that may be changed dynamically. However, it is nontrivial to analyze and predict any stocks, being time-varying and affected by unlimited factors in a given market. The portfolio management and subsequent trading decisions highly depend on the results of stock correlation analysis and price prediction. Stock correlation analysis and price prediction play an important role to achieve any profitable trading. It is difficult to achieve stable absolute returns in such a market. A number of rules and barriers exist in the Chinese A-share market such as trading restrictions and high fees, as well as scarce and expensive hedging tools. ![]() In this paper, we have implemented a high-frequency quantitative system that can obtain stable returns for the Chinese A-share market, which has been running for more than 3 months (from Mato June 30, 2020) with the expected results. ![]()
0 Comments
Leave a Reply. |
Details
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |