公开(公告)号：US20250117838A1

公开(公告)日：2025-04-10

申请号：US18422321

申请日：2024-01-25

Applicant: Oracle International Corporation

Inventor： Akash BAVISKAR ,  Krishnan RAMANATHAN ,  Vikas AGRAWAL ,  Dipawesh PAWAR

IPC: G06Q30/0601

Abstract: Embodiments classify a product to one of a plurality of product classifications. Embodiments receive a description of the product and create a first prompt for a trained large language model (“LLM”), the first prompt including the description of the product and contextual information of the product. In response to the first prompt, embodiments use the trained LLM to generate a hallucinated product classification for the product. Embodiments word embed the hallucinated product classification and the plurality of product classifications and similarity match the embedded hallucinated product classification with one of the embedded plurality of product classifications. The matched one of the embedded plurality of product classifications is determined to be a predicted classification of the product.

公开(公告)号：US20250013911A1

公开(公告)日：2025-01-09

申请号：US18233975

申请日：2023-08-15

Applicant: Oracle International Corporation

Inventor： Vikas AGRAWAL ,  Karthik Bangalore Mani ,  Krishnan Ramanathan

IPC: G06N20/00

Abstract: Embodiments generate a machine learning (“ML”) model. Embodiments receive training data, the training data including time dependent data and a plurality of dates corresponding to the time dependent data. Embodiments date split the training data by two or more of the plurality of dates to generate a plurality of date split training data. For each of the plurality of date split training data, embodiments split the date split training data into a training dataset and a corresponding testing dataset using one or more different ratios to generate a plurality of train/test splits. For each of the train/test splits, embodiments determine a difference of distribution between the training dataset and the corresponding testing dataset. Embodiments then select the train/test split with a smallest difference of distribution and train and test the ML model using the selected train/test split.

公开(公告)号：US20250014118A1

公开(公告)日：2025-01-09

申请号：US18461713

申请日：2023-09-06

Applicant: Oracle International Corporation

Inventor： Vikas AGRAWAL ,  Krishnan RAMANATHAN ,  Praneeth Medhatithi SHISHTLA ,  Jagdish CHAND

IPC: G06Q40/12 ,  G06N20/00

Abstract: Embodiments predict a target variable for accounts receivable using a machine learning model. For a first customer, embodiments receive a plurality of trained ML models corresponding to the target variable, the plurality of trained ML models trained using the historical data and comprising a first trained model having no grace period for the target variable and two or more grace period trained models, each grace period trained model having different grace periods for the target variable. Embodiments determine a Matthews' Correlation Coefficient (“MCC”) for the first trained model. When the MCC for the first trained model is low, embodiments determine the MCC for each of the grace period trained models, and when one or more MCCs for each of the grace period trained models is higher than the MCC for the first trained model, embodiments select the corresponding grace period trained model having a highest MCC.

公开(公告)号：US20250014097A1

公开(公告)日：2025-01-09

申请号：US18470555

申请日：2023-09-20

Applicant: Oracle International Corporation

Inventor： Vikas AGRAWAL ,  Krishnan RAMANATHAN ,  Praneeth Medhatithi SHISHTLA ,  Jagdish CHAND

IPC: G06Q40/03

Abstract: Embodiments analyze a customer of an organization. Embodiments select the customer and receive historical data corresponding to a plurality of transactions of the customer with the organization, the historical data including, for each of the transactions, a target variable including a number of days of delayed payment for each transaction. Based on the historical data, embodiments determine a cost of a delayed payment from the customer and determine an average delay of payments of the customer. Embodiments convert the cost of delayed payments to a first Z-score and the average delay of payments to a second Z-score. Embodiments then determine a reliability score of the customer comprising determining a Euclidean distance of the first Z-score and the second Z-score.

公开(公告)号：US20250014060A1

公开(公告)日：2025-01-09

申请号：US18236048

申请日：2023-08-21

Applicant: Oracle International Corporation

Inventor： Vikas AGRAWAL ,  Krishnan RAMANATHAN ,  Praneeth Medhatithi SHISHTLA ,  Jagdish CHAND

IPC: G06Q30/0204 ,  G06Q20/08

Abstract: Embodiments predict a target variable for accounts receivable in response to receiving historical data corresponding to a plurality of transactions corresponding to a plurality of customers, the historical data including, for each of the transactions, the target variable. Embodiments segment each of the customers based on the historical data corresponding to each of the customers, the segmenting including determining a variation of the target variable for each customer and, based on the variation, classifying each customer as having a low variation, a medium variation, or a high variation. For each low variation customer, embodiments create a regular ML model without a grace period that is trained and tested using the historical data. For each medium variation customer, embodiments create the regular ML model and create two or more grace period ML models, each grace period ML model adding a different grace period to the target variable.