Recommendation Systems Recommendation systems aim to identify items - - PowerPoint PPT Presentation

recommendation systems
SMART_READER_LITE
LIVE PREVIEW

Recommendation Systems Recommendation systems aim to identify items - - PowerPoint PPT Presentation

Improving Package Recommendations through Query Relaxation M A T T E O B R U C A T O U N I V E R S I T Y O F M A S S A C H U S E T T S , A M H E R S T , U S A A Z Z A A B O U Z I E D N E W Y O R K U N I V E R S I T Y , A B U D H A B I


slide-1
SLIDE 1

M A T T E O B R U C A T O U N I V E R S I T Y O F M A S S A C H U S E T T S , A M H E R S T , U S A A Z Z A A B O U Z I E D N E W Y O R K U N I V E R S I T Y , A B U D H A B I , U A E A L E X A N D R A M E L I O U U N I V E R S I T Y O F M A S S A C H U S E T T S , A M H E R S T , U S A P R E S E N T E D B Y :

MATTEO BRUCATO

m a t t e o @ c s . u m a s s . e d u

Improving Package Recommendations through Query Relaxation

slide-2
SLIDE 2

Recommendation Systems

— Recommendation systems aim to identify items of

interest to users

Recommended to me by Amazon before traveling to Hangzhou: 1

Improving Package Recommendations through Query Relaxation

slide-3
SLIDE 3

“Package” Recommendations

— But sometimes items are actually bundled together

in packages of items

Example 1 — Amazon bundles 2

Improving Package Recommendations through Query Relaxation

slide-4
SLIDE 4

“Package” Recommendations

— But sometimes items are actually bundled together

in packages of items

Example 2 — A flight package: *

* Recommended by Google Flights

3

Improving Package Recommendations through Query Relaxation

slide-5
SLIDE 5

“Package” Recommendations

— But sometimes items are actually bundled together

in packages of items

Example 3 — A meal plan: 4

Improving Package Recommendations through Query Relaxation

slide-6
SLIDE 6

A “Package” Query

— All recipes should have less than 25 g of fat — The entire meal plan should have:

¡ At least 1700 kcal in total ¡ Between 3 and 5 meals per day

— The meal plan should minimize the total preparation time

5

Improving Package Recommendations through Query Relaxation

slide-7
SLIDE 7

Many Feasible Solutions…

6

Improving Package Recommendations through Query Relaxation

slide-8
SLIDE 8

Too Many Feasible Solutions…

1704 feasible meal plans, with only 15 recipes

7

Improving Package Recommendations through Query Relaxation

slide-9
SLIDE 9

A New “Big Data” Challenge

— Usually we talk about:

¡ Lots of data ¡ Lots of features

— But what about:

¡ More combinations!

— Practical challenges of “more combinations”:

¡ Computational complexity ¡

8

Improving Package Recommendations through Query Relaxation

Usability

slide-10
SLIDE 10

What Could Systems Do?

9

Improving Package Recommendations through Query Relaxation

Query

  • ≥ 1700 kcal in total
  • Minimal prep. time

The dietitian might be willing to accept lower calories for lower preparation time

Top-1 meal plan 1,710 kcal 3 hrs 5 min

50 50 571 571 298 298 417 417 424 424 30 30 25 25 80 80

slide-11
SLIDE 11

What Could Systems Do?

10

Improving Package Recommendations through Query Relaxation

Top-1 meal plan 1,710 kcal 3 hrs 5 min

50 50 571 571 298 298 417 417 424 424 30 30 25 25 80 80

Out

1 hr less! Infeasible, but perhaps better than top-1

60 60 571 571 298 298 417 417 364 364 30 30 25 25 20 20

1,650 < 1,700 kcal 2 hrs 5 min

50 50 16.2 16.2 21 21 10.7 10.7

In

slide-12
SLIDE 12

Our Approach

11

— We propose a new use of query relaxation: — Usually we relax when:

¡ The query does not produce any result ¡ The query does not produce enough results

— Here, we relax to:

¡ Improve upon some aspect of the query result

Improving Package Recommendations through Query Relaxation

slide-13
SLIDE 13

Package Query Relaxations

Improving Package Recommendations through Query Relaxation

12

— What is a relaxation of a package query?

Package Query

  • Base Constraints – Each meal:
  • ≤ 25 g of fat in each meal
  • Global Constraints – The meal plan:
  • ≥ 1700 kcal in total
  • Cardinality Constraints:
  • 3 to 5 meals
  • Minimal preparation time

Constraints Objective

Coarse-grained Relaxation Fine-grained Relaxation

30

slide-14
SLIDE 14

Criteria for Relaxations

Improving Package Recommendations through Query Relaxation

13

— Relaxations modify the query and thus produce a

different result than the original query

— How do we pick a good relaxation?

¡ Relaxations should improve the result ÷ In some aspects specified by the query ÷ As much as possible ¡ But they may cause some error ÷ The total error should be as low as possible

slide-15
SLIDE 15

Impact of Coarse Relaxations

Improving Package Recommendations through Query Relaxation

14

— How much should we relax?

101 102 103 104 105 20 40 60 80 100

% change % relaxation

Improvement Error

Relaxing only a few constraints provides the highest impact Diminishing returns

More relaxed

slide-16
SLIDE 16

Review

Improving Package Recommendations through Query Relaxation

15

— Summary so far:

¡ Package recommendations ¡ Package query relaxations ¡ Relaxation trade-off

— Rest of the talk:

¡ How do users react to relaxations? ¡ Lessons and future work

user study

slide-17
SLIDE 17

How do users react to relaxations?

Improving Package Recommendations through Query Relaxation

16

— Two Research Questions:

① Are users willing to accept relaxations? ② Do they have preferences regarding the type of constraints to be removed?

Let’s ask the crowd!

slide-18
SLIDE 18

Dataset Description

Improving Package Recommendations through Query Relaxation

17

— Dataset

¡ 7,955 (arguably) tasty recipes extracted from allrecipes.com

slide-19
SLIDE 19

Task Instructions

Improving Package Recommendations through Query Relaxation

18

We automatically generated 50 unique task configurations:

We varied these 4 constraints

Cardinality Constraint

Objective

2 Base Constraints 2 Global Constraints

slide-20
SLIDE 20

Task Choices

Improving Package Recommendations through Query Relaxation

19

— For each of the 50 configurations, we showed

5 different meal plans, each removing one constraint only:

  • 1. ORIGINAL
  • 2. CARDINALITYRELAX
  • 3. BASERELAX
  • 4. GLOBALRELAX
  • 5. RANDOM

— We used colors to indicate constraints adherence or violation — Results were presented sorted by preparation time

No Relaxation

Removing the cardinality constraint Removing one base constraint

Removing one global constraint A random package

slide-21
SLIDE 21

Task Screenshots

Improving Package Recommendations through Query Relaxation

20 Global constraint violation and amount of violation Objective is highlighted GLOBALRELAX

slide-22
SLIDE 22

Task Screenshots

Improving Package Recommendations through Query Relaxation

21 CARDINALITYRELAX Objective got worse

slide-23
SLIDE 23

Task Screenshots

Improving Package Recommendations through Query Relaxation

22 BASERELAX

slide-24
SLIDE 24

Task Screenshots

Improving Package Recommendations through Query Relaxation

23 ORIGINAL Objective got even worse!

slide-25
SLIDE 25

Collected Data

Improving Package Recommendations through Query Relaxation

24

— Run on crowdflower.com — Each configuration completed by 10 unique workers — No worker allowed to complete more than 5

configurations

— We removed obvious spammers a posteriori:

¡ Same explanations in every task ¡ Random explanations ¡ Inconsistent explanations

— Resulting in 115 unique workers and 306 unique task

instances

slide-26
SLIDE 26

Evaluation

Improving Package Recommendations through Query Relaxation

25

— The ORIGINAL plan was rejected 30% of the time

① Are users willing to accept relaxations? ② Do they have preferences regarding the type of constraints to be removed? ① Are users willing to accept relaxations? ② Do they have preferences regarding the type of constraints to be removed? We need to provide users with alternatives!

slide-27
SLIDE 27

Evaluation

Improving Package Recommendations through Query Relaxation

26

— Relaxed plans were chosen 76% of the time

① Are users willing to accept relaxations? ② Do they have preferences regarding the type of constraints to be removed? ① Are users willing to accept relaxations? ② Do they have preferences regarding the type of constraints to be removed? More likely to choose a relaxed plan than the original!

70% 91%

■ When ORIGINAL is recommended ■ When ORIGINAL is not recommended

slide-28
SLIDE 28

Evaluation

Improving Package Recommendations through Query Relaxation

27

① Are users willing to accept relaxations? ② Do they have preferences regarding the type of constraints to be removed? ① Are users willing to accept relaxations? ② Do they have preferences regarding the type of constraints to be removed?

■ Overall ■ When ORIGINAL is recommended ■ When ORIGINAL is not recommended

BASERELAX GLOBALRELAX CARDINALITYRELAX

slide-29
SLIDE 29

Why Relaxations?

Improving Package Recommendations through Query Relaxation

28

— Lower preparation time was often the reason:

slide-30
SLIDE 30

Additional Lessons

Improving Package Recommendations through Query Relaxation

29

— Good explanations for the bias toward BASERELAX:

(The plans had to contain 4 meals)

The workers relaxed base constraints by transforming them into global constraints!

slide-31
SLIDE 31

Future Work

Improving Package Recommendations through Query Relaxation

30

— What dictates user’s sensitivity toward different

kinds of constraints?

— Impact of fine-grained relaxations — Reverse relaxations

¡ Tightening the constraints

— Additional relaxation methods

¡ Including the type of relaxation workers spontaneously applied

slide-32
SLIDE 32

Summary of Contributions

Improving Package Recommendations through Query Relaxation

31

— Novel application of query relaxation — Impact of coarse relaxations — User reaction to package relaxations

Thank you!

101 102 103 104 105 20 40 60 80 100

% change % relaxation Improvement Error