2020: An Algo Odyssey Presentation for Stanford University November - PowerPoint PPT Presentation

SECURITIES DIVISION 2020: An Algo Odyssey Presentation for Stanford University November 2020

Electronic FX Markets and Algos Confidential 2

Liquid currency pairs SECURITIES DIVISION Confidential Daily volumes Average Top of Book Spread (EURGBP example) Significant day on day changes in volumes executed electronically. Uneven distribution of volumes across currency pairs. 3

Market Microstructure I SECURITIES DIVISION Confidential Key Indicators: Market Volumes and Bid-Offer Spread Minute by Minute Intraday volume charts (EURUSD Average Top of Book Spread (EURGBP example) example) Pick high-volume periods of the day where possible for Pegged Wider top-of-book spread favours faster settings in Pegged algo and Hybrid Execution 4

Market Microstructure II SECURITIES DIVISION Confidential Key Indicators: Orderbook Depth and Imbalance Intraday orderbook depth (EURGBP Seasonal / intraday orderbook imbalance (EURUSD example) example) Orderbook depth is key to minimizing implementation shortfall of In markets with a significant orderbook imbalance, there is sweep-to-fill algos like Dynamic Aggressive potential price pressure that may favour an Iceberg 5

SECURITIES DIVISION Market seasonality and variability Confidential Adaptive aggress logic for dynamic hybrid FX markets exhibit • intra-day variability, • intra-week seasonality, • event-driven changes • month-end, quarter- end effects… Distribution of daily EURUSD volume by day of the week Intra-day top-of-book spread (HK time) Data source: EBS, Reuters. Data period: 05-Oct-2014 to 04-Oct-2019. 6 The information provided herein was supplied in good faith based on information which we believe, but do not guarantee, to be accurate or complete; however we are not responsible for errors or omissions that may occur. Past performance is not indicative of future results.

Mircrostrucure impact on algos SECURITIES DIVISION Confidential Liquidity supply and demand and intro to algos Algo Favoured by Live Orderbook Depth Market Activity Liquidity Conditions HIGH HIGH Dynamic Aggressive NORMAL HIGH Dynamic Hybrid Slower LOW HIGH Pegged Passive HIGH NORMAL Dynamic Aggressive NORMAL NORMAL Dynamic Hybrid Normal LOW NORMAL Pegged Neutral HIGH LOW Dynamic Aggressive NORMAL LOW Dynamic Hybrid Faster LOW LOW Pegged Aggressive 7

New Markets, New Algos Confidential 8

SECURITIES DIVISION Algos Learning from Algos I Confidential Adaptive aggress logic for dynamic hybrid • Slower/normal/faster modes of dynamic hybrid target given probability of aggressing top of book • Dynamic model uses a live metric of its aggress rate to update the aggress parameter in real time. Aggress parameter over time • What constitutes a better model: on NFP day • Mean closer to the target aggress probability • Standard deviation smaller Probability density NFP Data source: EBS, Reuters, GS. Data period: Jan 2019 to the present. 9 The information provided herein was supplied in good faith based on information which we believe, but do not guarantee, to be accurate or complete; however we are not responsible for errors or omissions that may occur. Past performance is not indicative of future results.

SECURITIES DIVISION Algos Learning from Algos II Confidential Dynamic Aggressive and Iceberg Sweep to Fill Logic • Pre-trade analytics on TED (right) estimates liquidity supply as a function of orderbook depth • Use first wave of algo aggress logic to verify the liquidity shown, or make adjustments as needed Data source: GS. Data period: Jan 2019 to the present. 10 The information provided herein was supplied in good faith based on information which we believe, but do not guarantee, to be accurate or complete; however we are not responsible for errors or omissions that may occur. Past performance is not indicative of future results.

SECURITIES DIVISION Smart NDF Algos Confidential Dynamic execution of NDF currenices 11 The information provided herein was supplied in good faith based on information which we believe, but do not guarantee, to be accurate or complete; however we are not responsible for errors or omissions that may occur. Data source: GS, primary markets. For illustrative purposes only.

SECURITIES DIVISION FX Basket algos Confidential Portfolio execution for FX 100.0% 90.0% 80.0% 70.0% USDCHF 60.0% USDNOK EURAUD 50.0% EURCAD 40.0% CADJPY 30.0% USDCAD 20.0% 10.0% 0.0% 21:36.0 28:48.0 36:00.0 43:12.0 50:24.0 57:36.0 04:48.0 12:00.0 19:12.0 Data source: GS. 12 The information provided herein was supplied in good faith based on information which we believe, but do not guarantee, to be accurate or complete; however we are not responsible for errors or omissions that may occur. For illustrative purposes only.

SECURITIES DIVISION FX Basket algos Confidential Trailing legs, detached legs Detached leg three normal, one trailing, one detached leg Trailing leg three detached legs Data source: GS. 13 The information provided herein was supplied in good faith based on information which we believe, but do not guarantee, to be accurate or complete; however we are not responsible for errors or omissions that may occur. For illustrative purposes only.

SECURITIES DIVISION Algos for FX options traders Confidential Gamma strategies and KI/KO conditions Data source: GS. 14 The information provided herein was supplied in good faith based on information which we believe, but do not guarantee, to be accurate or complete; however we are not responsible for errors or omissions that may occur. For illustrative purposes only.