Menu
Contact Us
Contact Us
Close
/ Menu
Products
Bespoke Products
Enterprise AI
Technology
Company
Case Studies
FAQ
Get Started
Explore FAQs by Topic
Quick Contact With Us!
Contact Us
FAQs
Contact Us
QDT FAQ
Quantum ML
Trade Analytics FAQ
Trade Analytics
Commodities Forecasting FAQ
Commodities Forecasting
Supply Chain Solutions FAQ
Supply Chain Solutions
CME DataMine Machine Learning as a Service FAQ
CME DataMine ML
QDT Algorithms
01.
Who is QDT?
QDT, or Quantum Data Technologies, is a leading innovator in AI and machine learning, offering a suite of solutions that empower users to harness predictive analytics and data science. Our flagship platform, Quantum Machine Learning (QML), enables the construction of custom AI and machine learning models tailored to unique business requirements.
02.
What makes QDT's QML platform unique?
QML stands out for its democratization of data science, providing immediate access to high-quality data, unparalleled customization, accelerated insights, cost-effectiveness, seamless scalability, and a supportive community. These features make advanced analytics accessible to a broader audience, from small firms to multinational corporations.
03.
How does QDT support marketing analytics?
QDT's Marketing Analytics Suite offers solutions like Media Mix Modeling, Marketing Personalization, Social Media Performance Analysis, and Price Elasticity Analysis. Each solution leverages QML to provide actionable insights, optimize marketing investments, and drive data-driven decision-making.
04.
Can QDT's solutions be applied to supply chain management?
Yes, QDT offers Predictive Supplier Insights (PSI), an AI-driven analytics solution for proactive supply chain management. PSI predicts and prevents supplier-related risks using advanced machine learning, ensuring supply chain continuity and efficiency.
05.
How does QDT assist in commodities forecasting and analytics?
Our solution for Commodities Forecasting and Analytics allows users to create custom predictive models or access QDT’s expert models. Enhanced with consulting services, it helps navigate commodities markets with accuracy and strategic insight.
06.
What is the Data Mine Machine Learning Service in partnership with CME?
In collaboration with CME Group, QDT launched the Data Mine Machine Learning Service, a platform providing sophisticated predictive analytics for trading insights. It features comprehensive data integration, unique data from CME, and advanced model-building capabilities for financial markets.
07.
How does QDT's technology support its solutions?
QDT's ecosystem includes a sophisticated data platform (Quantum DL), an Automated Machine Learning Engine (Quantum ML), and an intuitive UI/UX Platform Architecture. These technologies ensure seamless data analysis, predictive modeling, and user experience across QDT's offerings.
08.
What industries can benefit from QDT's solutions?
QDT's platform and solutions are versatile, benefiting a wide range of industries including marketing, supply chain management, financial services, commodities trading, and more. Any organization looking to leverage data science and predictive analytics can find value in QDT's offerings.
01.
What is Quantum ML?
Quantum ML is an automated machine learning platform that uses AI and machine learning to forecast time-series data and provide data-driven insights.
02.
Why Quantum ML?
Quantum ML simplifies and accelerates model-building workflows with a no-code, point-and-click interface. With Quantum ML, users can rapidly produce accurate and reliable forecasts, supported by transparent backtesting and performance metrics, enabling more confident and data-driven decision-making.
03.
Who can use Quantum ML?
Quantum ML eliminates the need for data science expertise to leverage machine learning. It empowers key decision-makers—such as procurement officers, buyers, traders, and analysts—who possess critical domain knowledge, putting the power of machine learning directly in their hands.
04.
What can I use Quantum ML for?
Quantum ML is used by some of the world’s leading enterprise institutions and individuals for trading, investment, procurement, hedging, budgeting and business forecasting.
05.
What is Automated Machine Learning?
Automated Machine Learning (AutoML) is a technology and software solution designed to simplify and expedite the workflows involved in building and maintaining machine learning models. It automates tasks such as data preprocessing, hyperparameter optimization, model creation, performance tracking, and ongoing updates.
06.
Why does Automated Machine Learning matter to me or my organization?
Building machine learning models typically requires a team of data scientists and substantial time and effort to implement and deploy at scale. With Quantum ML, both technical and non-technical users can accomplish in days what traditionally takes weeks or months. For technical users, it eliminates much of the manual data preparation and repetitive tasks, allowing them to focus on higher-value activities. For non-technical users, the intuitive point-and-click workflow and automatic updates empower them to leverage their domain expertise by selecting data and building models independently.
07.
How does Quantum ML work?
Quantum ML leverages Artificial Intelligence and Machine Learning to empower users to forecast a wide range of target variables. Data is automatically ingested daily to update models and generate signals for user-specified timeframes. These signals are transformed into strategies, backtested, and evaluated across multiple performance metrics, enabling users to make direct comparisons between data, models, and strategies. The results and insights are presented through a modern, intuitive charting and analytics dashboard for ease of reporting and seamless decision-making.
08.
What targets can Quantum ML forecast?
Quantum ML is capable of forecasting any time-series data, such as equities, indices, commodities, and currencies. Beyond these, the scope of time-series data extends to numerous other applications, including revenue, sales, and a variety of business performance metrics.
09.
How is Quantum ML hosted?
Depending on customer needs, goals and project and governance requirements, Quantum ML can be hosted as a Managed Cloud service or via an ‘On Premise’ deployment.
10.
How far into the future can Quantum ML forecast?
Quantum ML is capable of building models for any forecasting timeframe. Deployments range from 1-day forecasts to 360 days and even up to 5 years into the future. Different timeframes often require varying data inputs, particularly in terms of data frequency (daily, monthly, yearly, etc.).
11.
Can I use my own data?
Yes, this depends on the subscription or deployment type. Enterprise customers often integrate their own data or data from third-party providers they are already subscribed to, provided the necessary licenses are in place and governance policies are followed.
01.
What is QDT's Advanced Trade Analytics Platform?
QDT's Advanced Trade Analytics Platform is a sophisticated solution designed to revolutionize the analysis and forecasting of global trade dynamics. It integrates comprehensive data sources, including COMTRADE datasets, shipping logistics, and macroeconomic indicators, to provide unparalleled insights into trade flows and their economic implications.
02.
How does QDT ensure comprehensive data integration in its trade analytics?
Our platform integrates the COMTRADE dataset with external data sources such as shipping logistics and macroeconomic indicators from leading global institutions. This approach offers a 360-degree view of the trade ecosystem, enabling users to conduct in-depth analyses and gain actionable insights.
03.
What unique features does the Advanced Trade Analytics Platform offer?
Key features include advanced commodity analysis, dynamic vessel routing based on AIS data, and cloud-based scalability. This combination provides users with tools to improve supply chain and logistics operations, identify market trends, and make informed strategic decisions.
04.
How can organizations benefit from QDT's trade analytics solutions?
Organizations gain access to in-depth analyses of trade patterns, enabling the identification of market trends, risks, and opportunities. The platform supports informed decision-making regarding trade policies, market strategies, and investment opportunities, offering a competitive strategic advantage.
05.
Who can benefit from using QDT's Trade Analytics Platform?
The platform serves a broad spectrum of users, including policymakers, researchers, business professionals, and anyone involved in international trade. Its versatility and depth make it valuable for a wide range of applications, from strategic planning to operational efficiency improvement.
06.
How does QDT's solution accommodate the analysis of global trade flows?
By leveraging historical AIS data and integrating it with comprehensive datasets, our platform provides up-to-the-minute insights into shipping logistics and global trade flows. This enables users to forecast and strategize based on accurate, real-time information.
07.
What kind of support does QDT offer to users of its Trade Analytics Platform?
QDT provides robust support, including training materials, user guides, and dedicated customer service. We ensure users can maximize the platform's capabilities through comprehensive onboarding, ongoing assistance, and tailored consultancy services.
08.
Can the Trade Analytics Platform be customized to fit specific organizational needs?
Yes, our platform is designed with customization and flexibility in mind. Users can tailor analyses to specific commodities, markets, or geographic regions, ensuring that the insights generated are highly relevant and actionable for their unique strategic needs.
09.
How does the platform handle data security and privacy?
QDT adheres to stringent data security and privacy standards. The platform implements advanced encryption, user authentication, and compliance measures to protect sensitive information and ensure that users can confidently analyze and strategize based on trade data.
10.
How can companies get started with utilizing QDT's Advanced Trade Analytics Platform?
Interested companies can initiate the process by contacting QDT through our website or direct communication channels. We offer personalized demonstrations, pilot programs, and strategic consultations to ensure seamless integration and alignment with your trade analysis objectives.
01.
What makes QDT's commodities forecasting solutions unique?
QDT's commodities forecasting solutions stand out due to their integration of comprehensive data sources, advanced machine learning models, and the ability to customize these models to specific market analyses or trading strategies. Our solutions offer unparalleled accuracy, flexibility, and strategic insight, enabling users to navigate the complexities of the commodities markets successfully.
02.
How does QDT ensure the accuracy of its commodities forecasts?
Accuracy in QDT's forecasts is achieved through a combination of extensive data integration, sophisticated machine learning techniques, and continuous backtesting against historical data. Our models are refined and improved over time, incorporating new data and feedback to ensure reliability and precision in forecasting.
03.
Can users create their own predictive models for commodities forecasting on QDT's platform?
Yes, QDT empowers users to build their own machine learning models using our Quantum Machine Learning (QML) platform. This user-driven model development is supported by extensive data resources and advanced analytics tools, enabling customized solutions tailored to specific trading strategies and market analyses.
04.
What types of data does QDT use for commodities forecasting?
QDT utilizes a wide array of data sources for commodities forecasting, including market data, financial indicators, retail foot traffic, consumer sentiment, macroeconomic trends, and more. This diverse dataset ensures that our forecasts are comprehensive and take into account a broad spectrum of influencing factors.
05.
How do QDT's solutions accommodate changes in market dynamics or unforeseen events?
Our solutions are designed to be adaptive and responsive to changing market conditions. QDT's machine learning models can quickly incorporate new data, allowing for timely adjustments to forecasts in response to unforeseen events or shifts in market dynamics. This ensures that our clients can stay ahead with the most current insights and strategies.
06.
What consulting services does QDT offer to support commodities forecasting?
QDT offers tailored consulting services to help clients integrate our forecasting solutions into their workflows. These services include strategy development, deep dive analytics, driver analysis, and ongoing support to uncover underlying factors influencing market movements and to optimize forecasting and trading strategies.
07.
How do QDT's forecasting solutions handle different commodities markets?
Our platform is equipped to handle a wide range of commodities markets, including agricultural products, energy, metals, and more. The flexibility and scalability of our solutions allow users to adjust models for specific commodities, taking into account unique market drivers and conditions.
08.
How can businesses benefit from QDT's commodities forecasting solutions?
Businesses can gain a strategic edge by using QDT's forecasting solutions to anticipate market trends, optimize purchase and sales decisions, and refine trading strategies. Our accurate forecasts help in reducing risks, maximizing returns, and making informed decisions in the volatile commodities market.
09.
Are QDT's commodities forecasting solutions suitable for both traders and analysts?
Absolutely. Our solutions cater to a wide range of users, from traders looking for an edge in their trading strategies to analysts seeking deep insights into market dynamics and future trends. The platform's flexibility and depth make it a valuable tool for a diverse audience within the commodities sector.
10.
How can companies get started with QDT's commodities forecasting solutions?
Companies interested in leveraging QDT's commodities forecasting solutions can contact us through our website or directly reach out to our sales and support teams. We offer demonstrations, pilot programs, and customized onboarding processes to ensure that our solutions align with our clients' specific needs and strategic goals.
01.
What is QDT's approach to supply chain solutions?
QDT leverages artificial intelligence (AI) and machine learning to offer predictive supplier insights (PSI), a platform designed to enhance supply chain resilience. By predicting, preventing, and providing prognoses on supplier-related risks, our solutions ensure supply chain continuity and efficiency across various industries.
02.
How does the Predictive Supplier Insights (PSI) platform work?
PSI uses AI to anticipate risks across an extensive supplier network, employing over 150 data sources and 80 KPIs to predict potential disruptions. This comprehensive approach enables proactive risk management, ensuring operational resilience and efficiency.
03.
What types of risks can QDT's PSI platform identify and mitigate?
Our platform is equipped to identify and mitigate a wide range of risks, including logistical delays, quality issues, financial instability of suppliers, and external factors such as geopolitical tensions or natural disasters. This broad risk coverage ensures comprehensive protection for your supply chain.
04.
Can QDT's supply chain solutions be integrated with existing systems?
Yes, our supply chain solutions are designed for easy integration with existing ERP and SCM systems. This flexibility ensures that businesses can enhance their supply chain resilience without the need for extensive system overhauls or complex implementations.
05.
How do businesses benefit from using QDT's supply chain solutions?
Businesses benefit through enhanced visibility into supplier risks, improved decision-making capabilities, and the ability to preemptively address potential disruptions. This leads to more robust supply chain operations, reduced costs associated with supply chain failures, and ultimately, a more competitive position in the market.
06.
What industries are best suited for QDT's supply chain solutions?
Our supply chain solutions are versatile and applicable across a broad spectrum of industries, including manufacturing, retail, healthcare, automotive, and technology. Any business that relies on a complex network of suppliers can benefit from our predictive insights and risk management capabilities.
07.
How does QDT ensure the accuracy of its predictive analytics in supply chain management?
Accuracy is ensured through the continuous refinement of our AI models, incorporating real-time data, industry trends, and feedback from implemented mitigation strategies. This dynamic approach keeps our predictions relevant and reliable, helping businesses stay ahead of potential disruptions.
08.
What support and training does QDT offer for its supply chain solutions?
QDT provides comprehensive support and training, including onboarding sessions, detailed documentation, and customer support services. We ensure that our clients have the knowledge and resources needed to effectively utilize our solutions for maximum supply chain resilience.
09.
How does QDT's PSI platform handle data privacy and security?
Data privacy and security are paramount in all QDT solutions. Our PSI platform employs state-of-the-art encryption, secure data storage practices, and compliance with global data protection regulations to safeguard sensitive information.
10.
How can companies get started with QDT's supply chain solutions?
Companies interested in enhancing their supply chain resilience with QDT's solutions can reach out through our website or directly contact our sales team. We offer tailored demos, pilot projects, and strategic assessments to align our solutions with your specific supply chain challenges and goals.
01.
What is DataMine Machine Learning Service?
The DataMine Machine Learning Service is an Automated Machine Learning platform that uses CME Group data and other public data to build machine learning models for financial instruments such as equities, indices, commodities, currencies, and cryptoassets. You can access the service with this link.
02.
Why do I need DataMine Machine Learning Service?
The goal with DataMine Machine Learning Service is to enable anyone to derive meaningful data-driven insights for procurement, trading and risk management. The platform comes pre-loaded with a set of example models, and users can also build their own models; no coding or data science expertise required.
03.
What is Automated Machine Learning?
Automated Machine Learning is a technology that streamlines and accelerates the processes and workflow typically required to utilize machine learning. This involves the automation of data pre-processing, model creation, parameter adaptation, and model updates. Historically this process requires a team of Data Scientists and takes weeks or even months to implement. With Machine Learning Service, non-technical users can build and leverage machine learning models.
04.
How does DataMine Machine Learning Service work?
DataMine Machine Learning Service is a machine learning tool that allows users to build their own machine learning models. Once built, data is ingested automatically every day to update the models and generate daily signals for different timeframes specified by the user. Model signals are converted into strategies and then backtested and evaluated across a variety of performance metrics, allowing users to evaluate and compare different data, models and strategies.
05.
How is DataMine Machine Learning Service hosted?
The DataMine Machine Learning Service is hosted as a managed cloud solution.
06.
Who can use DataMine Machine Learning Service?
DataMine Machine Learning Service is designed to make machine learning accessible to non-technical users. With Machine Learning Service you don’t have to be a Data Scientist to utilize machine learning. Look at the user guide to learn more:
07.
Is DataMine Machine Learning Service also helpful for data scientists and other more advanced users?
Yes, DataMine Machine Learning Service streamlines and automates many of the steps in machine learning workflows, freeing up more advanced users to work on higher-value tasks such as signals processing and strategy implementation.
08.
How much does DataMine Machine Learning Service cost?
The DataMine Machine Learning Service is charged on a per-model basis. The cost has two components: an initial cost to build the model and an ongoing maintenance cost to update the models daily.
09.
Can I get trial access to the DataMine Machine Learning Service?
Yes, there is a one-week trial available for all new users. You must opt-out of the trial to avoid being charged. Contact a sales agent at cmedatasales.com for more details.
10.
How many users can DataMine Machine Learning Service support?
The DataMine Machine Learning Service can support any number of users. Licenses are sold on an individual basis.
11.
What financial instruments can DataMine Machine Learning Service build models for?
Please contact us for a complete list of instruments available for model building.
12.
How far into the future can DataMine Machine Learning Service predict?
Machine Learning Service can build models for any timeframe. Different timeframes generally benefit from different data inputs.
13.
How often are the models updated?
Models are updated every day. New data is ingested overnight, and the models update first thing in the morning to be available on the US market open.
14.
How many models can I build using the DataMine Machine Learning Service?
There is no limit to the number of models a user can build.
15.
How is model performance measured?
The DataMine Machine Learning Service is a tool. All models are measured via performance metrics and backtesting in order for users to make their own evaluation of the model performance and establish confidence in the tool. <see model backtesting>
16.
How many machine learning algorithms does DataMine Machine Learning Service use?
DataMine Machine Learning Service currently offers a library of algorithms as options when building a machine learning model. These include Gradient Boosting Regressors, XGB, LGBM, CAT boost, Extra trees, KNN, SVM, SVR, Linear Regression, Ridge Regression, Lasso Regression, Huber Regressors, and Neural Networks.
17.
What is the Markets Page?
The Markets Page is a high-level view of all available forecasts across categories and sectors. The primary goal of the Markets Page is to give users a directional indication of different markets. Additionally, users can toggle on or off labels for Signals and Accuracy, to see the respective signal strength and accuracy of forecasts at different time intervals.
18.
What is the Forecast Page?
The Forecast Page is a medium-level view of forecasts for specific target variables. The purpose of this page is to provide users with a more detailed illustration of the forecast shape (Prediction Curve), behavior and performance at different time intervals, as well as a historical record of the forecast backtesting over time.
19.
What is the Strategy Simulator Page?
The Strategy Simulator page is a tool that uses signal processing to turn model signals of various timeframes into actionable insights. It does this by combining signals from multiple models using different parameters and filters, so only the best model signals are used. Users are provided with default strategy parameters, but can further optimize strategies to their own individual goals, strategy preferences, and risk profile. Examples of strategy preferences:
Select which model signals are used in the strategy.
Optimize for different performance metrics such as NetPosition (Equity Curve), ROI, Sharpe Ratio, Information Ratio, Max Drawdown, etc.
Filter out model signals below certain performance thresholds.
Trade Long/Short, Long-Cash, or Short-Cash.
Trade only signals above or below certain thresholds.
20.
What is the Data Explorer Page?
The Data Explorer is a tool designed to aid users in exploring and navigating CME data available for modeling. The dashboard provides a classification Search function as well as helpful visual elements to help the user find what they are looking for, and see the structure and categorization of the available data.Data
21.
Is the input data included in the license cost?
Yes, input data is included in the license cost. Users are only charged for building models.
22.
What data is available through The Machine Learning Service?
For a complete list of available data, click here.
23.
How are the CME Group Rolling Futures Indices calculated?
The CME Rolling Futures Indices are designed to provide market participants with an indicator for investment performance in a single CME Market.
CME Rolling Futures Indices are calculated on 28 futures products across five different asset classes. The CME Rolling Futures Indices will be calculated for each Business Day, in accordance with the CME Globex Trading Schedule and follow a next month rolling schedule.
To maintain a continuity or pricing and account for contract expiry and movements in liquidity, a roll period is required. The roll period is designed to gradually transfer the weighting of the inputs from the Near Futures Contract to the Second Futures Contract prior to expiry. The weighting of the Near Futures Contract is 100% up until seven days to expiry. After this point 20% weighting is transferred to the Second Futures Contract on a daily basis. When the Near Futures Contract is 2 days to expiry, it will have a weight of 0% and the Second Futures Contract will have a weight of 100%.CME Rolling Futures Indices are calculated for the following products: Jeff Jensen - is it possible to scroll back up to the new table I put in the general section that outlines products?
24.
What frequency of data can/do the models use?
Machine Learning Service is capable of using data of different frequencies. While the models themselves update daily, the input data frequency ranges from daily, to weekly, monthly, quarterly, or annual data resolution.
25.
Can I use my own data?
Currently the solution does not support users ingesting their own data.Model Building
26.
Can I build my own models?
Yes, users can build and maintain their own machine learning models.
27.
How are models trained?
Models are trained on 5 years of historical data preceding the model Start Date (assuming the data is available). For example, if a model is built from Jan 1st, 2022, the model will be trained on historical data from Jan 1st, 2017. If historical data isn’t available going back that far, the model will train on what it is provided.
28.
How are the models backtested?
Model metrics are displayed in the dashboard to facilitate straightforward analysis and evaluation of model performance.
29.
How do I assess model performance?
The Machine Learning Service provides a list of performance metrics that are updated daily as a part of the model building/update process.
30.
Are my models saved?
With Machine Learning Service, all user created models are stored on the cloud. Models are backed up to hard storage periodically in case of system failure.
01.
How does QDT ensure data quality and relevance in its QML platform?
QDT prioritizes data quality by integrating with Quantum DL, a vast data lake that includes hundreds of data providers offering thousands of data sources. This ensures that our predictive models and analytics are informed by the most relevant, up-to-date, and clean data available, eliminating the complex steps of data collection and preprocessing.
02.
What is the Quantum Superforecasting (QSF) model, and how does it enhance Media Mix Modeling (MMM)?
Quantum Superforecasting (QSF) is QDT's cutting-edge solution for MMM, leveraging Automated Machine Learning to provide precise, actionable insights into sales forecasting, investment optimization, and driver analysis. It democratizes advanced analytics by enabling marketing teams to implement sophisticated models without needing data science expertise, thereby optimizing marketing investments and strategy.
03.
Can QDT's solutions handle large-scale data analysis and forecasting?
Yes, our solutions are built on scalable architectures designed to handle varying levels of complexity and data volume. This is achieved through our cloud-based deployment, leveraging Kubernetes for dynamic scaling and Cassandra for distributed data management, ensuring our platforms can support everything from small exploratory projects to extensive, intricate analyses.
04.
What methodologies does QDT employ for predictive analytics and machine learning?
QDT's methodologies include time-domain autocorrelation for predictor alignment, Automated Machine Learning (AutoML) for efficient model selection and training, Bayesian Optimization for hyperparameter tuning, and ensembled forecasting to integrate multiple models for improved accuracy and robustness against diverse data scenarios.
05.
How does QDT's Automated Machine Learning Engine (Quantum ML) streamline the model-building process?
Quantum ML automates the end-to-end process of applying machine learning, including model selection, feature engineering, model training, and hyperparameter tuning. This allows users to efficiently generate predictive models with minimal need for deep technical expertise, focusing instead on strategy and insights.
06.
What support does QDT offer for custom model development?
QDT provides comprehensive consulting services to assist clients in integrating Quantum ML into their workflows. This includes tailored strategy development and deep dive analytics to ensure that predictive models are precisely aligned with organizational goals and market dynamics.
07.
How does QDT's UI/UX Platform Architecture enhance the user experience?
Our UI/UX platform, built on the same codebase as our machine learning platform, offers an intuitive interface for data analysis and model interaction. Leveraging technologies like NGINX, Kubernetes, Dash, and Flask, it provides a seamless, navigable experience that allows users to access data points, run models, and visualize outcomes effortlessly, regardless of their technical expertise.
08.
What security measures does QDT implement to protect data and user privacy?
QDT adheres to the highest standards of security and regulatory compliance. Our platforms enable secure access to data lakes and machine learning models through REST APIs, ensuring data protection and privacy with personalized user access and data encryption techniques.
09.
How does QDT's solution adapt to evolving market conditions or new data?
Our platforms are designed for continuous learning and adaptation, refining models and strategies based on new data and market feedback. This ensures that businesses can stay ahead of market trends and leverage the most current insights for decision-making.
10.
How can businesses start utilizing QDT's machine learning and analytics solutions?
Businesses interested in leveraging QDT's solutions can reach out through our website or contact support. We offer training and support to pilot customers, ensuring a smooth integration of our technology into their existing operations and workflows.