With the rapid development of artificial intelligence, long short term memory (LSTM), one kind of recurrent neural network (RNN), has been widely applied in time series prediction. Like RNN, Transformer is designed to handle the sequential data. As Transformer achieved great success in Natural Language Processing (NLP), researchers got interested in Transformer's performance on time series prediction, and plenty of Transformer-based solutions on long time series forecasting have come out recently. However, when it comes to financial time series prediction, LSTM is still a dominant architecture. Therefore, the question this study wants to answer is: whether the Transformer-based model can be applied in financial time series prediction and beat LSTM. To answer this question, various LSTM-based and Transformer-based models are compared on multiple financial prediction tasks based on high-frequency limit order book data. A new LSTM-based model called DLSTM is built and new architecture for the Transformer-based model is designed to adapt for financial prediction. The experiment result reflects that the Transformer-based model only has the limited advantage in absolute price sequence prediction. The LSTM-based models show better and more robust performance on difference sequence prediction, such as price difference and price movement.

Are the humans of finance an endangered species? People are still the lubricant that oils the wheels of finance, toiling at innumerable tasks--executing and settling trades, writing analysis, monitoring risk. Squeezed by low interest rates, shrinking trading revenue, and nimbler technology-based competitors, banks are racing to remake themselves as digital companies to cut costs and better serve clients. In other words, they're preparing for the day that machines made by men and women take over more of what used to be the sole province of humans: knowledge work. Consider venerable State Street, a 224-year-old custody bank that predates the steam locomotive and caters to institutional investors such as pensions and mutual funds.

That's how XTX Markets Ltd. is using superior smarts to beat the faster speeds of many computerized traders to become a force in market making. Already, London-based XTX Markets Ltd. earlier this year was declared the world's fourth-largest spot currency trader with 7.6% of the spot FX market, according to a detailed story in Bloomberg. Now that it's become a major player in currencies, it's now eyeing expanding into the bond, commodities and stock markets. The firm describes itself as "a leading quantitative-driven electronic market-maker," for the purpose of providing "liquidity in the Equity, FX, Fixed Income and Commodity markets." As an electronic market maker, XTX has taken human decision-making out of trading, according to the company's Co-Chief Executive Officer Zar Amrolia.

People are still the lubricant that oils the wheels of finance, toiling at innumerable tasks--executing and settling trades, writing analysis, monitoring risk. Squeezed by low interest rates, shrinking trading revenue, and nimbler technology-based competitors, banks are racing to remake themselves as digital companies to cut costs and better serve clients. In other words, they're preparing for the day that machines made by men and women take over more of what used to be the sole province of humans: knowledge work. Consider venerable State Street, a 224-year-old custody bank that predates the steam locomotive and caters to institutional investors such as pensions and mutual funds. In February, State Street executives told analysts that after spending five years upgrading technology systems, they realized how much more could be done.

It represents a particular pure quantum state of a specific isolated system of one or more particles. By choosing a specific system of coordinates, e.g.