INSIDER TRADING DETECTION
Detecting insider trading of financial instruments is described. In an embodiment news event data is received from a sentiment index where each news event has at least one associated rating of a relationship between the news event and the financial instrument. For example, a numerical rating of confidence that the news event will influence volatility of the financial instrument and a numerical rating of how related a news event is to a particular company. In examples the news events are filtered using the ratings and remaining news events are used to identify potential insider trading where a price of an order within a time period before the news event differs by more than a threshold amount from a characteristic of the market after the news event. Parameters such as the time period and the threshold may be automatically adjusted using feedback data or may be dynamically user adjusted.
1 . A method, comprising:
receiving news event data and at least one associated rating of a relationship between the news event and a financial instrument which may be traded on a market;
checking that the at least one associated rating meets criteria;
identifying a plurality of orders for the financial instrument present in a time period defined according to a time stamp of the news event;
identifying, using a processor, an order from the plurality of orders as being potential insider trading by comparing a price position of the order with a characteristic of the market after the news event;
generating an alert for the order identified as being potential insider trading; and
displaying the alert at a display system, the alert comprising at least the associated rating.
2 . The method of claim 1 , further comprising:
receiving the news event data and the at least one associated rating in a real-time stream,
the alert being generated and displayed in real time for each order identified as being potential insider trading.
3 . The method of claim 1 , wherein the characteristic of the market is the price of the financial instrument in the market.
4 . The method of claim 1 , wherein the characteristic of the market is an index of the market.
5 . The method of claim 1 , wherein identifying the order from the plurality of orders as being potential insider trading comprises comparing a price position of the order with both a price of the financial instrument after the news event and an index of the market after the news event.
6 . The method of claim 1 , wherein the at least one associated rating is an impact rating indicating a confidence that a news event will influence volatility of the financial instrument.
7 . The method of claim 1 , wherein the at least one associated rating is a relevance rating indicating how strongly related to the news event the financial instrument is.
8 . The method of claim 1 , further comprising:
checking that the news event data meets a novelty condition by checking a novelty rating of the news event data.
9 . The method of claim 8 , further comprising:
calculating the novelty rating by comparing the news event data with historical news event data.
10 . The method of claim 1 , wherein the time period is defined according to a user input and the method further comprising receiving the user input.
11 . The method of claim 1 , wherein identifying the order includes identifying the order from the plurality of orders as being possible insider trading when the price position of the order differs by at least a variance threshold from a characteristic of the market after the news event.
12 . The method of claim 11 , further comprising updating the variance threshold automatically according to an observed frequency of identification of orders as being potential insider trading and according to a volatility indicator of the financial instrument.
13 . A method comprising:
receiving historical news event data and at least one associated rating of a relationship between the news event and a financial instrument which may be traded on a market;
checking that the at least one associated rating meets criteria;
receiving user input specifying a look back period and a variance threshold;
identifying, a plurality of orders for the financial instrument present in the look back period immediately before the time stamp of the news event; and
identifying, using a processor, an order from the plurality of orders as being potential insider trading if a price position of the order differs by at least the variance threshold from a characteristic of the market after the news event.
14 . The method of claim 13 , further comprising:
generating a graphical display of prices of the financial instrument which also shows the news event data and at least one associated rating.
15 . The method of claim 13 , further comprising:
generating an alert that includes details of the news event, of the order identified as being potential insider trading, and of the at least one associated rating; and
displaying the alert at a graphical user interface.
16 . The method of claim 14 , comprising:
saving the graphical display and details of the news event, of the order identified as being potential insider trading, and of the at least one associated rating for use in a case display of a graphical user interface.
17 . A system comprising:
an input arranged to receive news event data and at least one associated rating of a relationship between the news event and a financial instrument which may be traded on a market;
a processor arranged to check that the at least one associated rating meets criteria;
the processor being arranged to identify a plurality of orders for the financial instrument present in a time period defined according to a time stamp of the news event; and
the processor being arranged to identify an order from the plurality of orders as being potential insider trading by comparing a price position of the order with a characteristic of the market after the news event.
18 . The system as of claim 17 , further comprising:
a parameter setting engine arranged to automatically update a variance threshold using during the comparison process according to an observed frequency of identification of orders as being potential insider trading and according to a volatility indicator of the financial instrument.
19 . The system of claim 17 , further comprising:
a non-transitory memory arranged to store the order identified as being potential insider trading together with the news event data and the at least one associated rating.
20 . A web browser application stored in a non-transitory processor readable memory and at least partially executed on a processor to perform the method as recited in claim 1 .