One of the most valuable parts of attending a conference is the opportunity to meet others and build your network—and potentially even find new partners. The explicit goal of the Research Corporation for Scientific Advancement’s (RCSA) Scialog conferences is to foster collaboration between scientists with different specialties and approaches, and, working together with Datascope, the company has been doing so in a quantitative way for the last six years. Datascope designed a survey to run before and after each conference to determine the level of familiarity between each attendee, as well as the topics they were most interested in and the other attendees they’d like to discuss those topics with. After the survey, Datascope implemented and continues to adapt an optimization tool that takes the survey data along with other metadata to choose optimal large topic discussion groups and small breakout groups for the conference. Afterward, a second survey is taken to see the effects on the network of attendees. Brian Lange discusses how Datasope and RCSA arrived at the problem, the design choices made in the survey and optimization, and how the results were visualized. Along the way, Brian covers lessons learned and other problems where optimization may prove to be fruitful.

1. Using stochastic optimization to bring people together
The perfect conference
Brian Lange @ Strata San José 2017

2. who is this guy?

3. who is this guy?

4. who are these folks?

5. who are these folks?

6. Today

7. Today
- Case study: our work with Research
Corporation for Scientific Advancement (RCSA)

8. Today
- Case study: our work with Research
Corporation for Scientific Advancement (RCSA)
- Some high level explanation of the technique we
used (simulated annealing)

9. Today
- Case study: our work with Research
Corporation for Scientific Advancement (RCSA)
- Some high level explanation of the technique we
used (simulated annealing)
- Our vision of the role of a data scientist, and
how they interact with the people they’re
serving

10. Meet Richard*
*(bad) artist’s rendering

11. By Hbarrison (Own work) [CC BY-SA 4.0 (http://creativecommons.org/licenses/by-sa/4.0)], via Wikimedia Commons
Scialog

12. “Some of the goals of Scialog
conferences are to facilitate the
formation of new collaborative
teams, encourage sharing insights
and catalyze novel lines of research.”
Richard’s needs

13. Scialog Conferences
Solar Energy
Conversion
Molecules
Come to Life
Time Domain
Astronomy
2010 2011 2012 2015 2016

14. What’s different about Scialog

15. What’s different about Scialog
- big picture, cross disciplinary topics

16. What’s different about Scialog
- big picture, cross disciplinary topics
- small conferences (40–50 junior scientists,
10–15 senior. scientists)

17. What’s different about Scialog
- big picture, cross disciplinary topics
- small conferences (40–50 junior scientists,
10–15 senior. scientists)
- invite only

18. What’s different about Scialog
- big picture, cross disciplinary topics
- small conferences (40–50 junior scientists,
10–15 senior. scientists)
- invite only
- unconventional format

19. What’s different about Scialog
- big picture, cross disciplinary topics
- small conferences (40–50 junior scientists,
10–15 senior. scientists)
- invite only
- unconventional format
How well does this work?

20. Quantifying connection

21. Quantifying connection

22. Quantifying connection

23. Quantifying connection

24. Quantifying connection

27. before after

28. Scialog 2015: Molecules Come to Life

29. Scialog 2015: Molecules Come to Life
- 118 new conversations

30. Scialog 2015: Molecules Come to Life
- 118 new conversations
- 17 new collaborations

31. Scialog 2015: Molecules Come to Life
- 118 new conversations
- 17 new collaborations
- 100% growth from pre-conference

32. Scialog 2015: Molecules Come to Life
- 118 new conversations
- 17 new collaborations
- 100% growth from pre-conference
- 53.6% of attendees formed a new
collaboration with an attendee

33. measure improve

34. Mini Breakout Groups - round 1
A D G J
B E H K
C F I L
conference
attendees

35. Mini Breakout Groups - round 2
A
D G
J
B
E
H KC
F
I
L

36. Mini Breakout Groups - round 3
A
D
G
J
B
E
H
K
C
F
I
L

37. Are these good groups?
A
D
G
J
B
E
H
K
C
F
I
L

38. Is this a good group?
DJ F L

39. Is this a good group?
DJ F L

40. Is this a good group?
DJ F L
1

41. Is this a good group?
DJ F L
1
2

42. Is this a good group?
DJ F L
4
1
2

43. Is this a good group?
DJ F L
4
1
2
terribleness: 7

44. Is this a good group?
J F L
4
1
2
terribleness: 7

45. Is this a good group?
J F L
2

46. Is this a good group?
BJ F L
2

47. Is this a good group?
BJ F L
2
terribleness: 2

49. 14778213400262135041705388361938994140625 possible configurations

50. 14778213400262135041705388361938994140625 possible configurations
1.47 x 1040, or 14 duodecillion

52. quadrillions of years :(

53. terribleness
slope
intercept
optimization

54. DJ F L
4
1
2
terribleness: 7
0
1.75
3.5
5.25
7
JDFL

55. BJ F L
2
terribleness: 2
0
1.75
3.5
5.25
7
JDFL JBFL

56. 1
BJ C L
4
terribleness: 6
0
1.75
3.5
5.25
7
JDFL JBFL JBCL

57. 1
BJ C E
terribleness:1
0
1.75
3.5
5.25
7
JDFL JBFL JBCL JBCE

58. 4 4
KJ C E
terribleness:8
0
2
4
6
8
JDFL JBFL JBCL JBCE JKCE

59. slope
intercept
terribleness

60. slope
intercept
terribleness
🤔

61. enter:
simulated annealing

62. simulated annealing

63. simulated annealing
a type of stochastic optimization

64. simulated annealing
a type of stochastic optimization
stochastic optimization
algorithm with randomness
introduced to avoid getting caught
in local minima

65. temperature: 100
A D G J
B E H K
C F I L
terribleness: 350
previous terribleness: 350

66. temperature: 1001. make a random “move” from current
state
A D G J
B E H K
C F I L
terribleness: 350
previous terribleness: 350

67. temperature: 100
A
D G JB
E H K
C F I L
terribleness: 380
previous terribleness: 350
1. make a random “move” from current
state

68. temperature: 100
A
D G JB
E H K
C F I L
terribleness: 380
previous terribleness: 350
1. make a random “move” from current
state
2. check if the new state is better than the
previous

69. temperature: 100
A
D G JB
E H K
C F I L
terribleness: 380
previous terribleness: 350
1. make a random “move” from current
state
2. check if the new state is better than the
previous
3. If it is, keep it and skip ahead.

70. temperature: 100
A
D G JB
E H K
C F I L
terribleness: 380
previous terribleness: 350
1. make a random “move” from current
state
2. check if the new state is better than the
previous
3. If it is, keep it and skip ahead.
4. If not, there’s a chance we’ll still keep it,
depending on the temperature

71. temperature: 1001. make a random “move” from current
state
2. check if the new state is better than the
previous
3. If it is, keep it and skip ahead.
4. If not, there’s a chance we’ll still keep it,
depending on the temperature A
D G JB
E H K
C F I L
terribleness: 380
previous terribleness: 380

72. temperature: 1001. make a random “move” from current
state
2. check if the new state is better than the
previous
3. If it is, keep it and skip ahead.
4. If not, there’s a chance we’ll still keep it,
depending on the temperature
5. Stop when temperature is too low.
Otherwise, reduce temperature and
repeat.
A
D G JB
E H K
C F I L
terribleness: 380
previous terribleness: 380

73. temperature: 901. make a random “move” from current
state
2. check if the new state is better than the
previous
3. If it is, keep it and skip ahead.
4. If not, there’s a chance we’ll still keep it,
depending on the temperature
5. Stop when temperature is too low.
Otherwise, reduce temperature and
repeat.
A
D
G
JB
E H K
C F
I
L
terribleness: 243
previous terribleness: 380

74. temperature: 901. make a random “move” from current
state
2. check if the new state is better than the
previous
3. If it is, keep it and skip ahead.
4. If not, there’s a chance we’ll still keep it,
depending on the temperature
5. Stop when temperature is too low.
Otherwise, reduce temperature and
repeat.
A
D
G
JB
E H K
C F
I
L
terribleness: 243
previous terribleness: 243

75. ⏩ fast forward

76. temperature: 31. make a random “move” from current
state
2. check if the new state is better than the
previous
3. If it is, keep it and skip ahead.
4. If not, there’s a chance we’ll still keep it,
depending on the temperature
5. Stop when temperature is too low.
Otherwise, reduce temperature and
repeat.
A
D
G
J
B
E HK
C
FI
L
terribleness: 63
previous terribleness: 63

77. temperature: 31. make a random “move” from current
state
2. check if the new state is better than the
previous
3. If it is, keep it and skip ahead.
4. If not, there’s a chance we’ll still keep it,
depending on the temperature
5. Stop when temperature is too low.
Otherwise, reduce temperature and
repeat.
A
D
G
J
B
E
H
K
C
FI
L
terribleness: 194
previous terribleness: 63

78. temperature: 31. make a random “move” from current
state
2. check if the new state is better than the
previous
3. If it is, keep it and skip ahead.
4. If not, there’s a chance we’ll still keep it,
depending on the temperature
5. Stop when temperature is too low.
Otherwise, reduce temperature and
repeat.
A
D
G
J
B
E HK
C
FI
L
terribleness: 63
previous terribleness: 63

81. Not just for groups of things

82. Not just for groups of things
- circuit board designs

83. Not just for groups of things
- circuit board designs
- stock trading rules

84. Not just for groups of things
- circuit board designs
- stock trading rules
- anything which has a defined state, a “move” (aka
transition to another state), and a measure of goodness

85. very, very tweakable

86. very, very tweakable
- make “smarter-than-random” moves

87. very, very tweakable
- make “smarter-than-random” moves
- change the cooling function (reheat and cool)

88. very, very tweakable
- make “smarter-than-random” moves
- change the cooling function (reheat and cool)
- save best state so far and restart from it periodically

89. very, very tweakable
- make “smarter-than-random” moves
- change the cooling function (reheat and cool)
- save best state so far and restart from it periodically
- repeat many times from different random starting
states

90. very, very tweakable
- make “smarter-than-random” moves
- change the cooling function (reheat and cool)
- save best state so far and restart from it periodically
- repeat many times from different random starting
states
- etc…

91. DATA SCIENCE
PITFALL
WARNING
very, very tweakable
Icons by Andrea Novoa, Chris Kerr, and Ananth from The Noun Project
- make “smarter-than-random” moves
- change the cooling function (reheat and cool)
- save best state so far and restart from it periodically
- repeat many times from different random starting
states
- etc…

92. let’s talk more about
terribleness

93. client needs

94. client needs
- minimize how “connected” the
people in each group are

95. client needs
- minimize how “connected” the
people in each group are
- don’t want people to be in the
same group with somebody
twice

96. client needs
- minimize how “connected” the
people in each group are
- don’t want people to be in the
same group with somebody
twice
- etc…

97. client needs
- minimize how “connected” the
people in each group are
- don’t want people to be in the
same group with somebody
twice
- etc…
math/code

98. generate ideas
build prototypeevaluation
iterative problem solving
anticipate refining your solution
“what does Richard need?”

99. generate ideas
build prototypeevaluation
iterative problem solving
anticipate refining your solution
“these could be better”

100. generate ideas
build prototypeevaluation
iterative problem solving
anticipate refining your solution
“let’s tweak the optimization
technique”

101. generate ideas
build prototypeevaluation
iterative problem solving
anticipate refining your solution
“much better, what do
you think Richard?”

102. generate ideas
build prototypeevaluation
iterative problem solving
anticipate refining your solution
“pretty good, but
I don’t like ______”

103. generate ideas
build prototypeevaluation
iterative problem solving
anticipate refining your solution
“cool, let’s tweak the
objective function”

104. generate ideas
build prototypeevaluation
iterative problem solving
anticipate refining your solution
“these look great!”

105. generate ideas
build prototypeevaluation
iterative problem solving
“these are great!”
also an
optimization
algorithm of
sorts…

106. so, did it work?

107. Scialog 2015: Molecules Come to Life

108. Scialog 2015: Molecules Come to Life
- In 30 out of 39 group discussions (77%), none of the people
in those groups had even heard of each other before

109. Scialog 2015: Molecules Come to Life
- In 30 out of 39 group discussions (77%), none of the people
in those groups had even heard of each other before
- In all group discussions, no one had spoken or
collaborated with anyone else in their group

110. Scialog 2015: Molecules Come to Life
- In 30 out of 39 group discussions (77%), none of the people
in those groups had even heard of each other before
- In all group discussions, no one had spoken or
collaborated with anyone else in their group
- On average, a group had 2.6 different disciplines (physics,
biology, etc)

111. Scialog 2015: Molecules Come to Life
- In 30 out of 39 group discussions (77%), none of the people
in those groups had even heard of each other before
- In all group discussions, no one had spoken or
collaborated with anyone else in their group
- On average, a group had 2.6 different disciplines (physics,
biology, etc)
- Each group had at least one theorist and one
experimentalist

112. Scialog 2015: Molecules Come to Life
__________ is important to the success of Scialog
0
7.5
15
22.5
30
Very Much Disagree Neutral Very Much Agree
Mini Breakouts
Regular Discussions

113. Scialog 2015: Molecules Come to Life
“We received 20 collaborative
proposals, the most ever
at a Scialog.”

114. further iterations

115. A
D
G
J
B
E HK
C
FI
L
Tissue mechanics and evolution
The physics of genetic networks
In vivo mechanics
Topic groups/preferences

116. Topic A
Topic B
Topic C
Topic groups/preferences

117. Desired connections

118. Nominated topic experts

119. how might this work at a bigger conference?
- survey including EVERYONE not tenable
- use latent sources like social media
- use RFID or other hardware to infer connections at
the conference
- use a survey with a representative sample and
similarity metrics to project preferences

120. how might this work at a bigger conference?
- different format
- separate opt-in discussion track
- rather than groups, make email introductions

122. what to learn from this

123. optimization isn’t just for
straightforward
mathematical problems

124. data science isn’t just for
straightforward
mathematical problems

125. a great data scientist
acts as a translator

126. iteration drives
improvement on both
methods and data
collection

127. if you can measure it,
you have the data
to actively improve it

128. .co@bjlange
thanks!
questions?
brian [at] datascope.co