Augmenting missing values in historical or market data for deals

Patent metadata

Field	Value
Publication number	US-11257110-B2
Application number	US-202117153076-A
Country	US
Kind code	B2
Filing date	Jan 20, 2021
Priority date	Jun 24, 2016
Publication date	Feb 22, 2022
Grant date	Feb 22, 2022

Abstract

One embodiment provides a method for augmenting missing values in historical or market data for deals. The method comprises receiving information relating to a set of deals. For any service included in one or more deals of the set of deals but not included in one or more other deals of the set of deals, the method further comprises augmenting, for any or all of the one or more other deals that does not include the service, one or more missing values for the service with one or more recommended values based on a recommendation algorithm. The service may be at any service level of a hierarchy of services.

First claim

What is claimed is:

1. A method comprising:
receiving information relating to a set of service deals, wherein the information comprises, for each service deal of the set, corresponding metadata and one or more corresponding actual costs for one or more services of the service deal;
training a machine learning model by applying Naive Bayes algorithm to the information;
determining a first price for an in-flight deal based on the information;
receiving, as input, a user-specified second price for the in-flight deal; and
assessing competitiveness of bidding on the in-flight deal at the first price against bidding on the in-flight deal at the second price by:
predicting, via the machine learning model, a first probability of the service provider successfully bidding on the in-flight deal at the first price;
predicting, via the machine learning model, a second probability of the service provider successfully bidding on the in-flight deal at the second price; and
generating an output comprising the first probability and the second probability.

2. The method of claim 1 , further comprising:
for a service included in both the in-flight deal and a service deal of the set, augmenting one or more actual costs missing in the information with one or more recommended costs for the service.

3. The method of claim 2 , wherein the one or more recommended costs comprise one or more recommended unit costs.

4. The method of claim 2 , wherein the one or more recommended costs comprise one or more recommended baseline values.

5. The method of claim 2 , further comprising:
determining the one or more recommended costs via factorization through latent Dirichlet allocation (fLDA) using the information.

6. The method of claim 2 , further comprising:
determining a cost and a price of a service of the in-flight deal by mining actual costs for the service from the information and the one or more recommended costs; and
determining a total cost and a total price of the in-flight deal based on each cost and each price of each service determined, wherein the first price is based on the total cost and the total price.

7. The method of claim 1 , wherein the set of service deals comprises at least one of a historical deal or a market deal.

8. The method of claim 1 , wherein the output is a bar chart.

9. A system comprising a computer processor, a computer-readable hardware storage device, and program code embodied with the computer-readable hardware storage device for execution by the computer processor to implement a method comprising:
receiving information relating to a set of service deals, wherein the information comprises, for each service deal of the set, corresponding metadata and one or more corresponding actual costs for one or more services of the service deal;
training a machine learning model by applying Naive Bayes algorithm to the information;
determining a first price for an in-flight deal based on the information;
receiving, as input, a user-specified second price for the in-flight deal; and
assessing competitiveness of bidding on the in-flight deal at the first price against bidding on the in-flight deal at the second price by:
predicting, via the machine learning model, a first probability of the service provider successfully bidding on the in-flight deal at the first price;
predicting, via the machine learning model, a second probability of the service provider successfully bidding on the in-flight deal at the second price; and
generating an output comprising the first probability and the second probability.

10. The system of claim 9 , wherein the method further comprises:
for a service included in both the in-flight deal and a service deal of the set, augmenting one or more actual costs missing in the information with one or more recommended costs for the service.

11. The system of claim 10 , wherein the one or more recommended costs comprise one or more recommended unit costs.

12. The system of claim 10 , wherein the one or more recommended costs comprise one or more recommended baseline values.

13. The system of claim 10 , wherein the method further comprises:
determining the one or more recommended costs via factorization through latent Dirichlet allocation (fLDA) using the information.

14. The system of claim 10 , wherein the method further comprises:
determining a cost and a price of a service of the in-flight deal by mining actual costs for the service from the information and the one or more recommended costs; and
determining a total cost and a total price of the in-flight deal based on each cost and each price of each service determined, wherein the first price is based on the total cost and the total price.

15. The system of claim 9 , wherein the set of service deals comprises at least one of a historical deal or a market deal.

16. The system of claim 9 , wherein the output is a bar chart.

17. A computer program product comprising a computer-readable hardware storage device having program code embodied therewith, the program code being executable by a computer to implement a method comprising:
receiving information relating to a set of service deals, wherein the information comprises, for each service deal of the set, corresponding metadata and one or more corresponding actual costs for one or more services of the service deal;
training a machine learning model by applying Naive Bayes algorithm to the information;
determining a first price for an in-flight deal based on the information;
receiving, as input, a user-specified second price for the in-flight deal; and
assessing competitiveness of bidding on the in-flight deal at the first price against bidding on the in-flight deal at the second price by:
predicting, via the machine learning model, a first probability of the service provider successfully bidding on the in-flight deal at the first price;
predicting, via the machine learning model, a second probability of the service provider successfully bidding on the in-flight deal at the second price; and
generating an output comprising the first probability and the second probability.

18. The computer program product of claim 17 , wherein the method further comprises:
for a service included in both the in-flight deal and a service deal of the set, augmenting one or more actual costs missing in the information with one or more recommended costs for the service.

19. The computer program product of claim 18 , wherein the one or more recommended costs comprise one or more recommended unit costs.

20. The computer program product of claim 18 , wherein the one or more recommended costs comprise one or more recommended baseline values.

Assignees

• IBM

Inventors

• Fukuda Mari A
• Gajananan Kugamoorthy
• Jiang Shun
• Megahed Aly
• Nakamura Taiga
• Smith Mark A

Classifications

• G06F16/90324

  using system suggestions · CPC title

• G06Q30/0244 Primary

  Optimization · CPC title

• G06Q50/14

  Travel agencies · CPC title