Skip to content
Joseph asked Matt to compare the new tool with others he has used and categorize it.Matt emphasized the efficiency of quickly analyzing underlyings on the front end.
UX Interviews
Interview Summaries
Matt Williamson and Tradery Labs
Joe Reiss
May 13, 10:30 AM
English (Global)
4 Chapters
trading
strategy
back testing
tools
technical analysis
indicators
Overview
Introduction and Background:
Matt Williamson and Joseph Reiss, CEO of Tradery Labs, discussed the shift to AI-based trading technologies focused on automated trading strategies using AI since 2018.
Discussion on Trading Background and Tools Used:
Matt shared his experience in options trading and risk management, discussing backtesting tools like Thinkorswim and TradeStation. He highlighted strengths and weaknesses of platforms for charting and automation.
AI Technology Discussion:
Joseph introduced Sam as the head of product at Tradery Labs, discussing a research project on automated strategies built through AI learning algorithms tailored to individual traders' needs.
Product Demonstration Feedback Exchange:
Sam presented an AI workbench tool for technical analysis without needing a data science team. Matt provided input on optimizing features like profit percentage filters based on holding period preferences. The platform generates, refines, and evaluates trading models, incorporating numerical values like Sharpe ratio for better analysis, aimed at retail traders for subscription revenue.
Outline
Chapter 1: Background and Tools in Trading (00:25 - 08:02)
Matt Williamson discusses his systematic trading approach.
Tools like Strategy Quant and Thinkorswim are mentioned for strategy building and testing.
Chapter 2: Automated Trading Strategies (14:06 - 18:12)
Matt Williamson explains his use of an automated strategy alongside manual trading.
Mention of a complex flowchart for an option strategy.
Chapter 3: Importance of Back Testing (19:01 - 21:13)
Discussion on the significance of back testing for active trading strategies.
Introduction to a tool that allows for strategy building, automation, and optimization.
Chapter 4: Strategy Customization and AI Optimization (22:21 - 24:45)
Comparison between less customized AI-driven strategies and highly customizable manual strategies.
Consideration of utilizing strategies created by others and the level of customization desired.
Chapter 5: Technical Analysis and Model Development (27:54 - 46:18)
Overview of technical analysis and model development in progress.
Explanation of profit percentage, trade frequency, and learning thresholds in trading strategies.
Chapter 6: Charting and Strategy Sharing (47:20 - 56:10)
Presentation of charts showing trade outcomes and equity curves.
Proposal for social sharing of strategies and the business model for strategy development and execution.
Chapter 7: Feedback and Conceptualization (1:03:37 - 1:03:48)
Acknowledgment of feedback and discussion on the evolving concept of the trading platform.
Notes
📊 Research Project Introduction
Joseph Reiss explained the research project focusing on individuals with trading backgrounds.
The conversation was recorded for AI transcription and note-taking.
📈 Trader Background and Tools
Joseph discussed Matt Williamson's background as a trader and manager.
Matt mentioned using options as a tool for building and implementing strategies.
🔍 Strategy Building Process
Joseph asked Matt to explain the process of building a strategy from idea to live activation.
Sam Patel praised Matt's use of technical terminologies like curve fitting and backtesting.
🔄 Automated Strategies
Joseph and Matt discussed automated strategies and the importance of customization.
Matt offered to share a flow chart he created for an option strategy.
📉 Backtesting and Metrics
Joseph inquired about the importance of backtesting in trading strategies.
Matt mentioned using Collective2 and discussed the importance of volume.
📣 Communicating Risk to End Users
Sam and Matt discussed communicating risk factors and the need for clarity in setting parameters.
Matt suggested tooltips for providing guidance on accuracy.
📈 Visualizing Strategies
Sam discussed strategies in the context of back-end view and front-end presentation.
Matt highlighted the importance of proper labeling and numerical values in charting.
💼 Business Model Discussion
Sam explained the business model of strategy building and fine-tuning using the algorithm.
Matt acknowledged understanding the business model and expressed agreement.
🚀 Tool Evaluation and Feedback
📞 Conclusion
Joseph concluded the meeting, expressing satisfaction with the discussion.
Sam and Joseph mentioned staying in touch for future updates.
Action items
Matt Williamson
Consider relabeling 'time period' to 'back test length' (41:58)
Suggest using a slider with percent on the bottom and accuracy on top for profit percentage parameter (39:40)
Clarify that 'profit is 4%' refers to learning threshold, not actual profit (41:02)
Include a tooltip or note about expected sample size for optimal learning from trades based on set parameters (39:52)
Consider adding price of the underlying asset on top chart (53:17)
Toggle S&P, Nasdaq, or other indexes to compare performance vs. buy and hold strategy (53:32)
Sunish nambiar and Tradery Labs
Joe Reiss
May 13, 9:00 AM
English (Global)
4 Chapters
trading history
options strategies
backtesting
technical analysis
machine learning
strategy development
Overview
Sam Patel, Joseph Reiss, and Sunish Nambia discussed trading strategies and AI tool development. Sunish shared experience in capital markets, focusing on option trading in Indian markets. He detailed manual option strategy processes and software use for defining strategies efficiently. The group explored automating trading with AI, considering risk tolerance levels and backtesting importance. Sam presented an AI workbench for model building and automated strategy optimization.
The focus shifted to interpreting chart results showing wins vs losses distribution for automated strategies. Joseph sought clarity on effective data visualization for end-users. The meeting emphasized developing advanced tools for optimizing trading strategies. They discussed enhancing a backtesting strategy tool for clear presentation of investment, risk assessment, and profit analysis. Sam showcased options for strategy customization and chart interpretation.
They explored incorporating a social aspect for sharing strategies within the platform. Concerns arose about the fast-paced nature of trading and relying on personally tested strategies. A live demonstration of software "Obstra" was shown with features like option simulations and real-time market data integration. Future plans include more advanced features based on user feedback, aiming for valuable insights in trading scenarios. The session ended positively, planning to reconnect for further testing and collaboration opportunities.
Outline
Chapter 1: Introduction and Research Purpose (04:45 - 06:03)
04:45: Joseph Reiss explains the purpose of the call for research and seeks permission to record the conversation.
06:03: Sam Patel outlines the structure of the meeting, focusing on a Q&A interview followed by feedback on a product.
Chapter 2: Trading Strategies and Automation (08:36 - 16:21)
08:36: Discussion on options strategies and automation tools for trading.
11:27: SN explains the process of selecting options and analyzing strategies.
16:01: Joseph Reiss inquires about the technology stack used for strategy development.
Chapter 3: Product Feedback and Testing (17:36 - 26:15)
17:36: SN discusses testing strategies over different time frames.
22:50: Transition to discussing futures strategies and technical analysis for trading.
26:15: SN elaborates on strategy selection based on market trends and technical analysis.
Chapter 4: Strategy Simulation and Analysis (36:35 - 49:50)
36:35: Introduction to strategy simulations and interpreting results for profit and loss.
40:30: SN explains how historical data influences option strategies.
46:41: Sam Patel introduces automated strategies and their success rates.
Chapter 5: Backtesting and Strategy Summary (49:50 - 54:34)
49:50: Joseph Reiss emphasizes the importance of backtesting and strategy summaries.
53:16: Joseph Reiss discusses the need for a narrative-based summary of strategies.
54:34: Sam Patel highlights the feature of sharing strategies with team members and others.
Chapter 6: Closing Remarks and Appreciation (1:06:24 - 1:06:45)
1:06:24: Joseph Reiss thanks the participant for their time and insights.
1:06:45: SN expresses gratitude and concludes the conversation.
Notes
📊 Interview Structure
The meeting was divided into two parts: a Q&A interview style session led by Joseph Reiss and a product demonstration led by Sam Patel.
Joseph Reiss confirmed the recording of the call for research purposes.
📈 Trading Strategies
Sam Patel discussed building trading strategies, including the use of weekly expiries and calendar spreads.
Strategies focused on identifying directional movements and analyzing open interest.
💻 Tech Stack and Tools
Joseph Reiss inquired about the tech stack used for developing and testing strategies, mentioning the use of Abstra and Excel spreadsheets.
📈 Feedback on Product
Sam Patel demonstrated a tool for inputting data and technical indicators for machine learning, seeking feedback on its usability and communication of strategies.
📊 Improving Interface
Discussions included enhancing the interface to communicate strategy success rates clearly, such as incorporating graphical representations and narrative-based summaries.
🚀 Product Preference
Participants discussed preferences for automated tools and the importance of clear communication in presenting strategy outcomes to end-users.
Action items
Joseph Reiss
Confirm with Sunish that it's okay to film the call and use an AI note taker (05:49)
Kick off the meeting after confirming the recording permission (05:49)
Implement a summary on the right panel that is more narrative-based, explaining the story of the strategy (53:13)
Consider adding basic three or four parameters along with graphical representation for ease of understanding (52:55)
Incorporate features for social sharing and allowing users to follow other strategies (54:34)
Sascha Czerwenka and Tradery Labs
Joe Reiss
May 29, 10:00 AM
English (Global)
3 Chapters
AI Trading
Backtesting
Investment Strategies
Risk Tolerance
Product Development
Financial Advisory
Overview
The meeting between Joseph Reiss from Tradery Labs and Sascha Czerwenka covered introductions, Sascha's professional background in investments, discussion on AI and trading strategies, feedback on Tradery Labs' product features, a product demonstration, and plans for future meetings. Action items included closing the current scope, restarting for future meetings, and reaching out to Sascha for user testing in three months.
Notes
Edit
🔍 Introduction and Background (00:03 - 05:20)
Meeting initiated with recording consent.
Introduction of Joseph Reiss and Sascha Czerwenka, including their backgrounds.
Overview of Joseph's company, Tradery Labs, and their product development.
💼 Sascha's Professional Background (05:20 - 18:25)
Sascha detailed his experience working in a family office, handling various investment roles.
Transition to managing personal funds and working as a financial advisor on Upwork.
Discussion of his investment and trading strategies.
🧠 Discussion on AI and Trading (18:25 - 30:50)
Joseph explained the AI-driven trading model developed by Tradery Labs.
Sascha shared his thoughts on automation and AI in trading.
Exploration of potential concerns and interest in fully autonomous trading strategies.
💡 Product Features and Feedback (30:50 - 1:22:37)
Overview of Tradery Labs' product features, including asset selection, technical indicators, and risk tolerance.
Sascha provided feedback on improving the product, such as adding more detailed risk metrics and backtesting options.
Discussion on potential pricing models for retail investors and family offices.
📊 Product Demonstration (1:22:37 - 1:30:55)
Joseph demonstrated the AI workbench and backtesting features of the product.
Exploration of how to interpret backtest results and the importance of paper trading.
Discussion on future product iterations and additional features.
🔄 Next Steps (1:30:55 - 1:31:35)
Agreement to close the current scope and restart a new one for future meetings.
Plan to reach out to Sascha when the product is ready for user testing in approximately three months.
Action items
Joseph Reiss
Close the current scope and restart a new one for future meetings (1:31:09)
Reach out to Sascha when the product is ready for user testing in approximately three months (1:30:55)
Andrea Palladino and Tradery Labs
Joe Reiss
May 20, 8:00 AM
English (Global)
4 Chapters
q and A
recording
backtesting
indicators
strategies
model
Overview
Edit
Joseph Reiss from Tradery Labs discusses the company's pivot towards building software to expedite model creation for algorithmic trading. The new technology allows users to select assets, indicators, and train models with a drag-and-drop interface to streamline strategy development.
Andrew Palladino, an experienced part-time trader and machine learning enthusiast, provides insights on key backtesting metrics like profit ratio and drawdowns. He envisions a platform where users can build portfolios of automated strategies across various assets using cutting-edge technologies like reinforcement learning.
Joseph Reiss and Andrew Palladino discussed the dashboard screen design, asset selection, indicators, and risk management for a new trading product. They focused on features like customizable indicators, risk tolerance settings with quantifiable metrics like drawdowns, and trade frequency considerations.
The meeting progressed to evaluating backtesting results, equity curves, and strategy performance screens. Andrew suggested refining the user interface for better visualization of equity curves with associated risk metrics. The discussion highlighted the importance of clear risk assessment tools to complement trading strategies.
Outline
Chapter 1: Introduction and Overview (00:06 - 05:01)
Meeting introduction with recording consent and AI note-taking confirmation.
Discussion about the team's background in math and data science.
Chapter 2: Trading Strategy Development (08:22 - 16:06)
Andrew explains his process of enhancing an existing rule-based strategy.
Mention of capturing weekly range and performance tracking per strategy.
Chapter 3: Product Features and Backtesting (19:41 - 28:09)
Joseph discusses the selection of assets, indicators, and timeframe in strategy building.
Emphasis on risk management and desired features for risk assessment.
Andrew highlights the importance of capturing trends in trading strategies.
Chapter 4: User Interface and Strategy Selection (37:22 - 45:27)
Initial impressions and expectations for the product's home screen layout.
Discussion on strategy selection, feature customization, and automation.
Andrew's vision for integrating multiple strategies for various market conditions.
Chapter 5: Performance Metrics and Risk Analysis (51:56 - 55:50)
Importance of drawdown analysis and risk tolerance in strategy evaluation.
Andrew suggests detailed risk assessment features for traders.
Chapter 6: Model Training and Development Process (1:00:41 - 1:04:39)
Joseph seeks feedback on improving the model training process.
Focus on refining strategies and adjusting performance metrics.
Chapter 7: Strategy Overview and Backtest Analysis (1:11:04 - 1:17:04)
Overview of strategy selection and detailed backtest analysis.
Discussion on summarizing model design and providing backtest statistics.
Notes
📊 Meeting Overview
Recording the meeting for reference
**AI taking notes for report on product features
🔍 Initial Product Discussion
Selecting assets, markets, and indicators in the builder
Importance of automated strategy and backtesting
Feedback on product value and expectations
Dashboard layout preferences
📈 Risk Management Features
Discussion on risk dials and strategies
Importance of risk tolerance metrics
Detailed risk assessment for strategies
📉 Feedback and Follow-Up
Importance of key test metrics like max drawdowns
Yearly review concept with equity curve and heat map
Overview of specific strategies and sections
📋 Action Items
Follow-up and further discussion planned
Detailed strategy overview and analysis
🤖 Next Steps
Follow-up on feedback and implementation
Continued communication on product development
Action items
Edit
Andrew Palladino
Review the backtest (40:09)
Provide initial feedback on the dashboard screen (45:00)
Consider implementing a feature to train on drawdowns (1:03:36)
Suggest adding a way to warn users if the set profit target is unrealistic (1:07:56)
Recommend showing both equity value and drawdown percentage overlaid on one plot for better visualization (1:13:33)
Joseph Reiss
Provide an icon or pop-up explanation before allowing access to certain features for user understanding (1:06:59)
Adjust the visual representation of the equity curve in the overview section for more clarity (1:14:52)
Dmitry Karavaev and Tradery Labs
Joe Reiss
May 09, 10:00 AM
English (Global)
4 Chapters
trading
strategies
backtesting
tools
analysis
product
Overview
Meeting Summary:
Joseph Reiss and Sam Patel meet with Dmitry, a trader, to discuss algorithmic trading strategies. Reiss explains they build strategies without coding skills. Dmitry shares trading experience with tools like Metatrader and Bloomberg terminals, also using Python for strategies.
They discuss backtesting, strategy creation, risk tolerance, and visual trade data representation. Possibility of AI optimization is explored. Insights into potential Live trading integrations with Interactive Brokers are discussed.
Reiss and Patel present a futures trading platform for bitcoin and ETH minis, proposing a revenue-sharing model. They introduce a model where users can build models for free but pay to deploy them. The platform charges for active strategies.
Dmitry is interested in the free trial and suggests varying subscription fees based on portfolio sizes. Discussions on pricing models catering to different traders' profiles are held. Plans are made to involve Dmitry in testing the product once ready, emphasizing ongoing communication during prototype refinement.
Outline
Chapter 1: Overview of Algorithmic Trading Product (00:15 - 02:30)
Joseph Reiss introduces the purpose of the call and the development of algorithmic trading strategies.
Description of the software being built to simplify strategy creation without coding.
Chapter 2: Trading Experience and Strategies (03:33 - 08:03)
Dmitry shares his trading experience using Excel sheets and fundamental analysis.
Discussion on the process of building trading strategies and the tools used.
Chapter 3: Automated Strategies and Backtesting (14:01 - 19:24)
Dmitry mentions some automated trend following strategies.
Importance of key metrics in backtesting before deploying strategies to the market.
Chapter 4: Product Interface and Features (21:17 - 27:30)
Sam Patel discusses the front end of the product and its learning loop for strategy improvement.
Explanation of technical indicators and strategy generation using historical data.
Chapter 5: Backtesting and Strategy Performance (37:07 - 44:42)
Importance of analyzing the total potential growth and performance metrics of strategies.
Dmitry suggests showing the number of trades per period to evaluate strategy performance.
Chapter 6: Business Model and Future Steps (47:16 - 56:27)
Discussion on integration with Interactive Brokers and sharing profitable strategies.
Overview of the business model with active and in-progress strategies for user feedback and deployment.
Notes
📊 Overview of the Call
Joseph Reiss provided a brief overview of the call structure.
The call involved discussing trading history and showcasing a product being developed.
🔄 Experience with Trading
Dmitry shared his experience with trading, including using excel sheets and specific strategies.
Discussion on tools used for testing trading ideas such as Tradingview for technical analysis.
💻 Tools and Strategies
Questions on the process of building trading strategies, including the tech stack used.
Mention of using code and support tools like Excel and Tradingview for strategy development.
🔍 Top Metrics for Backtesting
Discussion on key metrics in a backtest and criteria for deploying strategies to the market.
Emphasis on understanding the process from idea generation to deployment.
📈 Product Presentation
Sam Patel discussed showcasing the product's interface to Dmitry for feedback.
Focus on the front end development and gathering insights from the user.
🔄 Strategy Development
Dmitry provided feedback on strategy fine-tuning and data visualization for different strategies.
Mention of the connection between Twitter Labs and Interactive Brokers for strategy implementation.
🚀 Business Model Feedback
Sam Patel sought feedback on the business model from Dmitry.
Discussion on active and upcoming strategies, and potential collaboration.
🌟 Next Steps
Plans to have users physically use and deploy the product once ready.
Well wishes exchanged for the project's success.
Action items
Edit
joseph reiss
Ensure to turn the sound back on if it cuts off (01:33)
Investigate potential ways to optimize strategies without overfitting (09:55)
Dmitry
Provide more details about the tool used for trading analysis and testing (05:35)
Consider utilizing Tradingview for technical indicator analysis (11:43)
Explore AI tools for simplifying strategy creation but be cautious with implementation challenges (13:42)
Recommend starting with higher subscription fees for big traders before adjusting for smaller traders (55:06)
Sam Patel
Implement a revenue sharing model for strategy creators (50:02)
Determine subscription fees based on backtesting balance and trader type (53:30)
Consider different subscription fees for traders with varying portfolio sizes (54:20)
Ali Asad and Tradery Labs
Joe Reiss
May 09, 9:00 AM
English (Global)
4 Chapters
trading strategies
technical analysis
backtesting
tools
risk tolerance
automated strategies
Overview
Ali Asad discussed his interest in trading options, emphasizing the use of technical and fundamental analysis, focused on long-term trends and risk management. He expressed a desire to automate trades but lacked programming skills. Joseph Reiss delved into Ali's trading routines, stressing the importance of strategy selection, risk tolerance, and backtesting. Sam Patel presented an automated strategy-building platform concept, discussing features like AI workbench creation, risk evaluation parameters, and visualization preferences for trade performance data. Ali provided feedback on trade data visualization preferences, including histograms or line charts, and discussions extended to revenue models based on user subscriptions.
The meeting revealed insights about market segmentation considerations, potential subscription costs ranging from $12-$30 monthly, and pricing structures based on portfolio sizes and management fees comparisons. Ali's approach of using technical analysis for forex and fundamental analysis for equities was scrutinized for compounding profits for retirement. Joseph and Sam provided in-depth insights into trading routines, tools, and automated strategy-building platforms. The outcomes of the meeting included aligning subscription costs with different investor profiles and exploring revenue models based on user subscriptions rather than profit-sharing agreements.
Ali, Joseph, and Sam collectively addressed themes surrounding trading strategies, risk management, automation, and revenue models, focusing on personalized strategies, backtesting, and visualization preferences. The meeting emphasized the importance of understanding trading routines, risk evaluation, and considerations about market segmentation. Insights were shared on creating personalized strategies without coding knowledge, integrating technical indicators, and backtesting results display methods. Overall, discussions centered on enhancing trade performance data presentation, user subscription revenue models, and pricing structures based on portfolio sizes and management fees comparisons.
Outline
Chapter 1: Investment Strategy Overview (01:46 - 05:52)
01:46: Joseph Reiss inquires about the ultimate goals and targets for investing.
04:02: Ali Asad-BOK Conv explains his trading approach, focusing on correlation analysis and trend following methods.
05:52: Joseph Reiss asks about the tools used in trading strategies.
Chapter 2: Risk Management and Backtesting (06:16 - 13:08)
06:16: Ali Asad-BOK Conv mentions using risk management formulas and basic correlation analysis.
08:46: Ali Asad-BOK Conv expresses interest in learning backtesting without coding.
11:51: Ali Asad-BOK Conv discusses key metrics he would like to see in backtests.
Chapter 3: Automated Strategy Building Tool (17:46 - 25:34)
17:46: Sam Patel introduces the AI workbench tool for building automated strategies.
24:25: Sam Patel explains filtering events to learn from profitable trades.
Chapter 4: Strategy Performance Visualization (33:04 - 41:56)
33:04: Sam Patel discusses assessing strategy performance with hypothetical investment scenarios.
36:01: Ali Asad-BOK Conv suggests using line charts for trade performance visualization.
41:40: Sam Patel emphasizes strategy evaluation and sharing features.
Chapter 5: Business Model and Strategy Sharing (44:03 - 50:56)
44:03: Sam Patel outlines the business model focusing on strategy creation and sharing.
46:50: Ali Asad-BOK Conv queries about revenue generation from shared strategies.
50:56: Joseph Reiss mentions exploring different markets and pricing strategies for the product launch.
Notes
📊 Investment Strategy
Ali Asad-BOK Conv uses multi-day candlesticks and trend following for equities.
Incorporates risk management formulas in Excel.
Considers combining technical chart measures with fundamental factors for decision-making.
🛠️ Tool Development
Sam Patel discusses a tool designed for building automated strategies without coding experience.
Tool allows selection of assets like Apple, Ethereum, and bitcoin, along with technical parameters and risk tolerance.
Workflow involves selecting timeline, defining risk tolerance, and training the algorithm on data.
🔍 Performance Metrics
Emphasis on backtesting with key metrics like profit and loss, max drawdown, and risk ratios.
Prioritizes strategies historically yielding daily returns.
📈 Model Customization
Sam Patel aims for user control over model details and training process.
Discusses fine-tuning the model for optimal performance and user comfort.
📈 Strategy Sharing
Tool allows sharing strategies with other users.
Potential for tokenization mentioned for strategy sharing and automation.
Strategy sharing involves providing account number and link for implementation.
Action items
Edit
Ali Asad-BOK Conv
Consider learning backtesting strategies (08:46)
Explore options for automating trades using platforms like Wanda and Interactive Brokers (10:25)
Prefer an oversight role in strategy creation with AI executing based on set rules and risk management (15:56)
Sam Patel
Implement a feature to allow clickable bar charts for detailed positive/negative trade views (37:09)
Joe Reiss
May 09, 9:00 AM
English (Global)
4 Chapters
trading strategies
technical analysis
backtesting
tools
risk tolerance
automated strategies
Overview
Ali Asad discussed his interest in trading options, emphasizing the use of technical and fundamental analysis, focused on long-term trends and risk management. He expressed a desire to automate trades but lacked programming skills. Joseph Reiss delved into Ali's trading routines, stressing the importance of strategy selection, risk tolerance, and backtesting. Sam Patel presented an automated strategy-building platform concept, discussing features like AI workbench creation, risk evaluation parameters, and visualization preferences for trade performance data. Ali provided feedback on trade data visualization preferences, including histograms or line charts, and discussions extended to revenue models based on user subscriptions.
The meeting revealed insights about market segmentation considerations, potential subscription costs ranging from $12-$30 monthly, and pricing structures based on portfolio sizes and management fees comparisons. Ali's approach of using technical analysis for forex and fundamental analysis for equities was scrutinized for compounding profits for retirement. Joseph and Sam provided in-depth insights into trading routines, tools, and automated strategy-building platforms. The outcomes of the meeting included aligning subscription costs with different investor profiles and exploring revenue models based on user subscriptions rather than profit-sharing agreements.
Ali, Joseph, and Sam collectively addressed themes surrounding trading strategies, risk management, automation, and revenue models, focusing on personalized strategies, backtesting, and visualization preferences. The meeting emphasized the importance of understanding trading routines, risk evaluation, and considerations about market segmentation. Insights were shared on creating personalized strategies without coding knowledge, integrating technical indicators, and backtesting results display methods. Overall, discussions centered on enhancing trade performance data presentation, user subscription revenue models, and pricing structures based on portfolio sizes and management fees comparisons.
Outline
Chapter 1: Investment Strategy Overview (01:46 - 05:52)
01:46: Joseph Reiss inquires about the ultimate goals and targets for investing.
04:02: Ali Asad-BOK Conv explains his trading approach, focusing on correlation analysis and trend following methods.
05:52: Joseph Reiss asks about the tools used in trading strategies.
Chapter 2: Risk Management and Backtesting (06:16 - 13:08)
06:16: Ali Asad-BOK Conv mentions using risk management formulas and basic correlation analysis.
08:46: Ali Asad-BOK Conv expresses interest in learning backtesting without coding.
11:51: Ali Asad-BOK Conv discusses key metrics he would like to see in backtests.
Chapter 3: Automated Strategy Building Tool (17:46 - 25:34)
17:46: Sam Patel introduces the AI workbench tool for building automated strategies.
24:25: Sam Patel explains filtering events to learn from profitable trades.
Chapter 4: Strategy Performance Visualization (33:04 - 41:56)
33:04: Sam Patel discusses assessing strategy performance with hypothetical investment scenarios.
36:01: Ali Asad-BOK Conv suggests using line charts for trade performance visualization.
41:40: Sam Patel emphasizes strategy evaluation and sharing features.
Chapter 5: Business Model and Strategy Sharing (44:03 - 50:56)
44:03: Sam Patel outlines the business model focusing on strategy creation and sharing.
46:50: Ali Asad-BOK Conv queries about revenue generation from shared strategies.
50:56: Joseph Reiss mentions exploring different markets and pricing strategies for the product launch.
Notes
📊 Investment Strategy
Ali Asad-BOK Conv uses multi-day candlesticks and trend following for equities.
Incorporates risk management formulas in Excel.
Considers combining technical chart measures with fundamental factors for decision-making.
🛠️ Tool Development
Sam Patel discusses a tool designed for building automated strategies without coding experience.
Tool allows selection of assets like Apple, Ethereum, and bitcoin, along with technical parameters and risk tolerance.
Workflow involves selecting timeline, defining risk tolerance, and training the algorithm on data.
🔍 Performance Metrics
Emphasis on backtesting with key metrics like profit and loss, max drawdown, and risk ratios.
Prioritizes strategies historically yielding daily returns.
📈 Model Customization
Sam Patel aims for user control over model details and training process.
Discusses fine-tuning the model for optimal performance and user comfort.
📈 Strategy Sharing
Tool allows sharing strategies with other users.
Potential for tokenization mentioned for strategy sharing and automation.
Strategy sharing involves providing account number and link for implementation.
Action items
Edit
Ali Asad-BOK Conv
Consider learning backtesting strategies (08:46)
Explore options for automating trades using platforms like Wanda and Interactive Brokers (10:25)
Prefer an oversight role in strategy creation with AI executing based on set rules and risk management (15:56)
Sam Patel
Implement a feature to allow clickable bar charts for detailed positive/negative trade views (37:09)
Andrew M and Tradery Labs
Joe Reiss
May 09, 8:00 AM
English (Global)
4 Chapters
trading
quantitative model
fundamental analysis
back testing
tools
strategy development
Overview
Tradery Labs Meeting Summary:
Joseph Reiss introduces Tradery Labs as a tech-focused company automating quantitative trading model creation to enhance efficiency. Andrew shares his experience as a consultant and high net worth portfolio manager, focusing on manual construction of quantitative models using tools like Factset for long-term and swing trading. Joseph explains their software's capabilities to automate strategy development through AI workbench, with users selecting assets, indicators, and timeframes.
Andrew emphasizes risk tolerance measurement through drawdowns and volatility for better decision-making, excluding unpredictable days like earnings day. They discuss event frequency's impact on learning opportunities and its translation into software UI. Sam and Andrew delve into visual representations of trading strategies through backtesting, analyzing potential growth, success rates, and trends over time, focusing on accurate labeling for comprehension.
The team explores implementing successful strategies into live trading using platforms like IBKr or Coinbase, with insights on subscription fees based on profitability. They emphasize continuous model updates for optimized performance and long-term strategy refinement driven by AI learning. Joseph Reiss expresses gratitude to Andrew as they conclude the meeting, discussing future product enhancements and testing phases for a more user-friendly experience in subsequent collaborations.
Outline
Chapter 1: Trading Experience and Strategies (03:57 - 21:39)
03:57: Introduction and request for consent to record the call.
07:39: Discussion on quantitative model development using analysts' history.
13:23: Description of end-to-end trade process including risk framework.
15:19: Emphasis on fundamental analysis in the trading strategy.
21:39: Transition to discussing strategy automation and back testing.
Chapter 2: Strategy Automation and Back Testing (21:54 - 26:20)
21:54: Exploration of automation possibilities and time constraints.
24:02: Implementation of rigorous back testing for strategy refinement.
25:55: Importance of strategy relevance and performance evaluation.
Chapter 3: Software Tool Prototype Presentation (28:06 - 53:16)
28:06: Conceptualization of an input tool for strategy creation and testing.
36:22: Suggestions for modular strategy development in the software.
39:46: Explanation of selecting timeframes and advanced options.
53:16: Transition to back testing strategies within the software platform.
Chapter 4: Strategy Evaluation and User Feedback (53:29 - 59:46)
54:05: Discussion on interpreting strategy success rates.
56:32: Introduction to sharing and leveraging strategies on the platform.
59:46: Reflection on learning outcomes from previous months.
Notes
📊 Introduction and Consent
Joseph Reiss asked for consent to record the call and use an AI note taker.
Andrew agreed to recording the call.
📈 Discussion on Trading Experience
Joseph Reiss inquired about Andrew's experience with trading.
Andrew mentioned focusing on fundamental work, risk overlay, and entry/exit points in his trading strategy.
🔧 Tools and Methodologies
Joseph Reiss asked Andrew about the tools he uses, including Excel, research reports, and company websites.
Andrew mentioned using GPT for quick answers but not extensively.
🤖 Automation Preferences
Joseph Reiss discussed automation tools and coding skills with Andrew.
Andrew emphasized consistency as a key factor in his trading approach.
🔍 Strategy Building
Joseph Reiss outlined a tool for building strategies with input parameters and technical indicators.
Andrew suggested a smartphone app-like interface for the tool.
🎯 Feedback on Demo Interface
Andrew raised questions about the distinction between signals and strategies in the demo interface.
Sam Patel explained the algorithm's search parameters and outcomes.
📈 Success Metrics
Andrew suggested labeling a metric as "success rate" in the software.
Sam Patel elaborated on multiple social elements in strategy development.
🤝 Closing Remarks
Andrew wished good luck to the team at the end of the meeting.
Action items
Edit
Joseph Reiss
Follow up with Sam for the head of product introduction (05:40)
Discuss backtesting methodologies and strategies (23:52)
Obtain feedback on customization preferences and risk tolerance levels for trading algorithms (32:46)
Sam Patel
Clarify the distinction between signals and strategies in the tool interface (38:01)
Explain how algorithm learning works based on profit percentage settings (46:44)
Consider adding more context or explanations for better understanding (52:20)
Explore options for visual representation of numbers like t ratios, drawdowns, etc. (56:11)
Want to print your doc?
This is not the way.
This is not the way.
Try clicking the ⋯ next to your doc name or using a keyboard shortcut (
CtrlP
) instead.