A method and system provide the ability to deliver media content. Input data is ingested and includes raw data for household locations and marketing data. The input data further consists of physical out-of-home activity data from advertisement exposure and business points of interest visitation, and digital internet based online activity data. The ingestion is performed through a pre-setup process that identifies a data delivery format, a data schema, and a linking key used in a Graph within a database. The input data is processed by determining when new data is ready for ingestion, identifying a file source, extracting the input data from the file source, and importing and storing the extracted input data into the Graph using the key. The input data is linked in the Graph. Measurements and analytics are generated and provide a measurement of exposure to and effectiveness of delivered media content.

The subject technology predicts consumer sentiment based on demographics and other statics features of the consumer as well as dynamic features generated based on engagement of the consumer with previously presented targeted content. The sentiment predictions are used to recommend and generated new targeted content that is published to the consumer.

A system and method for predicting prices for commodities in a computing environment is disclosed. The method includes obtaining supply chain attributes associated with a product from internal and external data sources. The method further includes predicting current demand value of the product based on the supply chain attributes using artificial intelligence-based models. Further, generating an optimum price value for the product based on the current demand value. Additionally, computing average price value at a regional level for the product based on regional product information retrieved from one or more local authority databases using artificial intelligence-based models. The method further includes determining a best suitable price value. Also, simulating the best suitable price value for the product in a simulation environment using one or more artificial intelligence-based models. Furthermore, the method includes generating a final price value.

Users form custom-defined communities for performing a defined activity amongst themselves. An actor defines the activity and restrictions associated with the activity. Members of the community place requests for the actor to perform member-specific actions during the activity on behalf of the members. The actor performs the activity with the member-specific actions and arranges procurement of results associated with each of the members. The actor and the members may also settle up with one another at least upon procurement. The activity is crowd sourced within the custom-defined community, thereby reducing the need for the members to each individually perform the activity.

Systems and methods disclosed herein provide automatic expense categorization of transactions or expenditures based on a machine learning (ML) model trained using anonymized transactional data for expenditures that are stored in a public blockchain. The anonymized transactional data for the expenditure and the expense category, may be distributed throughout the blockchain network and recorded in the blockchain. In some implementations, an expenditure may be submitted to the blockchain network for expense categorization. The transactional data for the expenditure may be anonymized to remove confidential and personal identifying information (PII) before it is distributed throughout the blockchain network. Each participating node of the blockchain network may utilize the ML model to identify an expense category for the expenditure. The participating nodes may provide a consensus mechanism in order to arrive at a shared understanding of how to categorize the expenditure.

The present disclosure relates to improving recommendations for small shops on an ecommerce platform while maintaining accuracy for larger shops. The improvement is achieved by retraining a machine-learning recommendation model to reduce sample selection bias using a meta-learning process. The retraining process comprises identifying a sample subset of shops on the ecommerce platform, and then creating shop-specific versions of the recommendation model for each of the shops in the subset. Each shop-specific model is created by optimizing the baseline model to predict user-item interactions in a first training dataset for the applicable shop. Each of the shop-specific models is then tested using a second training dataset for the shop. A loss is calculated for each shop-specific model based on the model's predicted user-item interactions and the actual user-item interactions in the second training dataset for the shop. A global loss is calculated based on each of the shop-specific losses, and the baseline model is updated to minimize the global loss. The model includes small and large-shop weight parameters that are applied to user-item interaction scores and that are learned during the re-training process.

Systems, methods, and apparatuses for generating a consumable product quotation are provided. An example method may include receiving a surface status. The example method may also include determining, by processing circuitry, consumable product requirements for performing a job based on the surface status and consumable product parameters accessed in a consumable products database. The example method may also include providing the consumable product requirements for output to a user. The consumable product requirements may include types of consumable products for completing the job.

A method of displaying a symbol representative of changes in price during a time period in which a highest price occurred at a first time within the time period, a lowest price occurred at a second time within the time period, and a last price occurred at a third time within the time period, the method includes receiving a bid price and an ask price corresponding to a fourth time within the time period, wherein there is no new last price corresponding to the fourth time, determining whether the last price is lower than the bid price or higher than the ask price, in response to the determining that the last price is not lower than the bid price and not higher than the ask price, updating the last price to correspond to the fourth time, and generating, by a charting engine, the symbol by drawing, at a first luminosity level, a spatiotemporal relationship between the highest price, the lowest price, and the last price in accordance with a selected symbol rendering method, in response to the determining that the last price is lower than the bid price or higher than the ask price, generating an estimated last price from the bid price and the ask price, the estimated last price corresponding to the fourth time, and generating, by a charting engine, the symbol by drawing, at a second luminosity level, a spatiotemporal relationship between the highest price, the lowest price, and the estimated last price in accordance with a selected symbol rendering method, and displaying, by the charting engine, the generated symbol at a particular position.

A system, a method and a computer program product are provided to determine user profile of one or more users in one or more buildings, using a machine learning model. The system may include at least one memory configured to store computer executable instructions and at least one processor configured to execute the computer executable instructions to obtain mobility features associated with the one or more buildings in a geographic region. The processor may be configured to determine using a trained machine learning model, one or more transport modes for the one or more buildings. The processor may be further configured to obtain indoor mobility data of the one or more users based on the one or more transport modes for the one or more buildings. The processor may be further configured determine the user profile of the one or more users in the one or more buildings.

Embodiments provide interactive methods and systems for exploring ideologies on a virtual map. Method performed by a processor of an ideology exploration system includes displaying an interactive map comprising a plurality of regions on a UI in an electronic device for a user. Each region is associated with at least one ideology attribute. Each region includes media items associated with the ideology attribute. The method includes facilitating a virtual tool for the user for navigating from one region to another region based on a user preference. The user preference includes actions performed by the user on regions for exploring the regions. The method also includes tracking a user identifier associated with the user based on the user preference to determine a journey of the user. The method further includes updating a status of the user on a user profile based on the journey of the user in the interactive map.