Sia Partners Science Catalog
TABLE OF CONTENTS
OUR DATASCIENCE APPROACH
GLOBAL OVERVIEW OF OUR BOT FACTORY
CAPTURE – Insurance Pricing
CAPTURE – RegWatch
VISUALIZE – Weather & Climate
INTERACT – R-Bot
INTERACT – Recruitment Chatbot
ANALYZE – Fraud Detection
ANALYZE – Image Recognition
PRICE – Motor Insurance Pricing
PREDICT – Parking Availability
Our datascience approach
Datascience expertise based on Sector Knowledge
• Energy & Utilities
• Transport, Industry & Retail
An understanding of the whole data value chain
• Data Acquisition
• Data Processing
clients trust us
• Data Modeling
• Data Visualization
A quick glance at our Bot Factory, please visit
d ata s c i e n ce- l a b .s i a - p a r tn er s .co m
We enable business activities with AI based use cases…
• Segmentation / Profiling
• Perception Study
• Targeting / Client Life-value
• Satisfaction Investigation
• Geo-Marketing Implementation
• Electronic Reputation
FORECAST & ASSET MANAGEMENT
• Consumption Forecast
• Process Performance Measurement
• Predictive Maintenance
• Entity Operational Monitoring
• ST and MT optimization
• Analysis & visualization of time series
REVENUE MANAGEMENT & PRICING
• Uncommon behaviors
• Measuring Demand Elasticity
• Fraud Detection
• Revenue Management
• Data Quality
• Dynamic Pricing
…thanks to an internal and operational Platform (PaaS)
Monitoring Dashboards (python, R scripts)
Include market data in your pricing model
Market prices are
a leading piece
in a competitive
Systematic use of the Internet to compare offers, coupled with the possibility
to henceforth terminate policies at any
time, may generate a competitive shock
in the individual insurance market.
Knowledge and consideration of competitors’ prices may become necessary
to not lose ground to market players holding such information.
Sia Partners has developed an innovative data capture technology to collect
Internet prices and a high expertise in
including this data into the pricing process. Sia Partners provides its clients
with its technology in order to assist
them with their pricing strategy within
this new competitive environment.
An innovative technology designed for a
• omparing prices on the internet is already a common practice that will become sysC
• ree cancellation may translate into substantially higher cancellation rates, up to a
OUR DATA CAPTURE SOLUTION
1. Collecting: prices are extracted through our data capture technology from
online quoting websites and price-comparators (car, home, health, loan insurance,…).
2. Storage: the collected information (prices, guarantees, offer, options) are
stored and historicized within an internal database.
3. Analysis: the pricing model and the business strategy are decrypted (pricing
structure, variables impact & interactions, zoning, vehicle clustering, exclusions,
4. Application: models and algorithms allowing the consideration of external
data have been developed in order to include market data within the pricing
Which applications ?
Sia Partners provides its data capture technology and its technical expertise within
packaged pricing offers.
• Technical benchmark against market models (pricing variables,
interactions, impact levels)
• Pricing and business strategy analysis
• Modelling price elasticity
• Including market prices (position, pricing gap,…)
• Building a customer value algorithm
• Building the pure premium model
• Including market models (zoning, vehicular,…)
• efining strategical segments and target positioning
• ollow-up of the strategy with respect to the market prices
Data Capture – Use Cases
Geography is a highly discriminant feature in car insurance. Taking geography
into account can be performed through
a zoning which assigns a pricing modulation coefficient to each zip code.
A robust estimation on each of the 6 300
zip codes seems barely feasible in regards to the required data volume. Market approaches mainly head towards a
residuals spatial smoothing or a demographic-based classification (density,
agglomeration type,...). However, these
approaches lie on strong and hardly verifiable assumptions.
Data capture makes the zoning building
reliable through external data integration with the market zonings. Data capture may thus be seen as an indirect
means to access other players’ portfolio
• Mapping the technical model residuals
• Building the zoning with spatial smoothing (Gaussian kernel)
• Selection of market zonings (key players, similar guarantees,…)
• Extracting and reconstructing the retained market zonings
• Identifying the deviations between technical and market
• Investigating the gaps on robust points
Joint zoning Technique & Market
Application of a credibility model based on the following principles:
• ach zip code coefficient matches a weighting between technical and market zonings’
• he weighting depends on the robustness of the technical zoning estimated from the
company internal data.
Price elasticity model
The price impact on the customer’s behavior constitutes a critical piece of information for the gross premium positioning.
The customer behavior is taken into account within the pricing process through
a price elasticity model which aims to describe the subscription, cancellation and renewal dynamics.
Sia Partners has developed a price elasticity model that includes the market prices
from the data capture on one of its customers’ home insurance product.
Variables relative to pricing positioning are
displayed among the 10 most explanatory
variables of the cancellation model. Moreover, the model analysis highlights an
increasing importance of these variables
over time. The customer behavior evolution and the cancellation facilitation lead
us to conclude this trend could continue
The developed model can predict the
impact of the pricing adjustments on
the cancellation rate of every customer
profile, including taking into account the
competing offer in the market.
The model has been used in order to aim
for two specific profiles during the annual
• rofiles which are strongly sensitive
to the price for which any increase
could translate into a substantial rise
• rofiles which are poorly sensitive to
the price and then likely to go through
a price increase without any substantial impact on cancellations.
Data capture reveals its potential within
the gross premium positioning through
developing quantitative models taking
into account the other market players’
Automate Banking Regulatory Watch
Keeping up with the volatile regulatory environment
Between 2014 and 2020, 77 major regulatory texts were published or are expected,
exclusively in the banking sector. More
than 2500 minor publications complete
No matter the industry (insurance, banking,
energy, retail, telecom, ...), keeping up with
this tsunami of publications is tough, and
teams spend a tremendous amount of time
for low added-value tasks such as detecting
and prioritizing new texts. This is where data
science demonstrates its efficiency: the
substitution of humans on time-consuming
tasks with low added-value.
Processing. An alert module by e-mail
makes it possible to be warned according
to several criteria to be defined.
Number of Major Regulatory Texts for
Thus, Sia Partners has developed a regulatory watch bot capable of aggregating
all new publications into a database.
These publications are then analyzed
and processed by several algorithms of
Machine Learning and Natural Language
Banking Industry (US & EU)
A wide set of technologies for the purpose of tracking regulation
Data collection on the web via web scrapping
Language detection of the article and indexation of
Automatic summary of the article for a fast restitution
of its main information
Classification of the article based on the content
Preparation of the mailing list
Link article content with the individual user preferences
for a personalized restitution of regulatory information
Management of users based on their preferences and roles in the company
Intelligent search of publications recorded in the tool
Daily alerts based on specific criteria chosen by each individual users
A functional and scalable framework to stay close to business needs
A web robot collects all the
documents published on
targeted sites every day.
The websites are referenced
in a single document easy to
edit. Thus, adding a new site
is quick and effortless.
The items collected (articles,
PDF, …) are stored in a dedicated NoSQL database.
Machine Learning Algorithms
analyze documents to
• dentification of topics
• argeting of relevant
• Automatic synthesis
An ecosystem of web-services for operational users
plugged into the database :
• Dedicated Search Engine
• Targeted Mailing & Alerting
• Dashboard for regulatory
RegWatch - Possibilities
Find any article with a dedicated
A fully customizable experience to
use the tool to its full extent
Using the powerful combination of Mongo DB and Elasticsearch, all the publications are indexed to enable access
through keywords and tags. Any article
can be accessed through the search engine, with numerous filter possibilities,
among which the publication date or the
source of the article.
Users may have specific needs regarding their own regulatory monitoring.
The RegWatch bot allows you to offer
customizable alerts, displaying only
the most relevant content to the right
person. Through a graphical user interface, users can choose their publication
sources or content to monitor. This setting allows the definition of email alerts
summarizing the most relevant new publications.
– Archive regulatory publications
– Customization and automatic alerts
Scalability & flexibility
A modular bot to adapt to a changing
The bot needs to grow along with the
needs of its users and new sources must
be easily added. Hence, the set up of
sources to track is handled by a single
configuration file, making it effortless to
increase the number of sources. Every
module used by the bot is coded as its
own service, which prevents any conflict
when adding or removing a feature. The
bot is currently retrieving more than 200
articles every week from about 35 sources
and new sources are added every month.
Test our RegWatch BOT
You can have an overview of our application at the following link:
WEATHER & CLIMATE
Master your weather sensitivity
products to answer
A bot which updates a
reference database of
weather data daily
Weather and Climate have major impacts on the business of companies in
a wide variety of sectors, ranging from
Insurance to Energy & Utilities, and including Transport & Retail.
DATA OF DIFFERENT NATURE
A REFERENCE DATABASE…
Weather forecasts for predicting
weather-sensitive phenomena on a
short term basis using deterministic approaches.
Available products: AROME, ARPEGE, GFS
Sia Partners’ database is remarkably
diverse and complete since it contains:
• ore than 30 distinct weather variables
• p to 40 years of history (since 1979)
• global geographic coverage
Meteorological observations and past
replays for assessing weather-sensitive
phenomena on a medium term basis
using probabilistic approaches.
Available products : ERA INTERIM, CFS
… UPDATED ON A DAILY BASIS
MULTIPLE WEATHER VARIABLES
• ay+4 time horizon
• ourly time step
• eather tiles and time-series data
Weather-sensitive companies leverage
weather data by mixing it with their business data in order to better understand
business essentials, find new valuable
insights, operate and maintain more efficiently distributed assets, anticipate
customer demand and/or mitigate business risks.
Energy & Utilities
“Minimize balancing costs”
“ rice a risk premium related
to natural disasters”
• Solar Irradiation
Transport & Industry
“ dapt time schedules during
“ djust stocks regarding
To face all these challenges, our Data
Science team offers a comprehensive
and diverse collection of weather data.
• Cloud Cover
… and many others!
Every 6 hours, Sia Partners’ bot collects
and processes around 10 Gb of weather
Weather & Climate – Use Cases
Energy & Utilities
Energy & Utilities
Using short term weather forecast
for crisis management
Short and medium term renewable
energy production simulator
Assessment of weather-related
delays on construction projects
Utility networks are particularly exposed
to extreme climatic conditions: strong
wind, snow or extreme temperatures
may damage facilities (for instance
power lines) and disrupt the power supply for a large number of customers.
Weather data is at the core of renewable
energy forecasts, the two prominent
technologies being wind and solar production assets.
All construction projects are directly impacted by climatic hazards, which may
cause delays of several weeks on initial
A simulation tool modeling 300+ production technologies helps to plan activities
over several years and select areas of interest for implementing a National Energy Transition Plan by testing the bulking
effect and the probability of occurrence
of extreme production scenario (either
low or high).
Companies are responsible for their project duration and have to estimate the
delays that may occur with respect to the
weather. They can also decide to postpone the start of a project in order to take
advantage of milder climatic conditions
on the key phases of the project.
– System Operators
– Governmental Energy Agency
By anticipating over-thresholds on those
weather variables in the next 4 days,
the crisis management department
may prioritize actions, optimize human
and technical resource allocation and
shorten reaction time for maintenance.
– Construction projects
Test our Weather & Climate BOT
By combining the work of our Weather BOT and the dataviz skills
of our Datascience Team, you can now watch the D+4 weather
forecast of the Eleonore windstorm in January 2018.
A Regulatory Compliance Assistant
A volatile regulatory environment leads to an extensive scope for
MAJOR REGULATORY TEXTS FOR COMPLIANCE (US & EU)
KNOW YOUR CUSTOMER
AML-CTF & 4th directive
Knowledge and Change Management Process need to be optimized
A MASSIVE EFFORT TO BE
LIMITED BY CLASSICAL KNOWLEDGE PROCESS
A formal requirement of training, especially by
US Regulations, for a wide and diverse target a
Regulations complexity, with diverse sources of
knowledge: Texts, Policies and procedures, Training packs, Legal Memos, Q&A…
A lack of Expert Compliance resources available, which causes inefficiencies in training
• Training Packs
• perational Policies & Procedures
• xpert Sessions “face-to-face” trainings
Multiple questions to Compliance Advisors through various channels: emails, phones,…
• nswers often take several days
• trong workload with a low added value
Sia Partners Approach: Reinforcing Knowledge and Change Management
Process by automating and customizing collaborators recurrent Q&A
A digital training companion
R-bot increases awareness by enhancing the existing training and advisory
set-ups, thanks to a day-to-day approach.
Collaborators can interact with R-bot
on various issues: Regulatory Requirements, Internal policies and Control
Plans, Operational Processes.
Regulatory bots are highly customizable
according to the needs and policies of
R-Bot – Use Cases
R-bot’s main features
A COMPLETE, UNIFIED AND STRUCTURED
DATABASE to aggregate data from diverse sources:
• Regulatory requirements
• nternal policies and procedures
• ontrol and reporting requirements
• ompany-specific use cases
A USER-FRIENDLY AND HIGHLY TRAINED
The bot will include two layers of
• he Sia Partners’ ready-to-use database
based on the knowledge of its Banking &
• A collaborative construction in order to
cover internal policies & processes information.
R-BOT IS EMBEDDED IN YOUR COLLABORATORS WORKING ENVIRONMENT
R-bot is an augmented Q&A, able to interact with collaborators through NLP,
with answers validated beforehand by
A Powerful Change Management
& Training Tool as a complement
to existing set-ups facilitates raising awareness.
A time saving tool for Compliance Officers, which acts as a
first filter for regulatory, relieving
Compliance teams who will have
more time to spend on topics
where their expertise is most valuable.
Real-time answers for collaborator, instead of time consuming
documentation research or Compliance support process.
Sia Partners in a few
• A Pioneer of Consulting 4.0 with 20+
Bots developed and an objective of 100
• A Recognized Banking expertise supported by Data Science teams.
• An Agile Approach to conduct Innovative Projects, proven for major clients.
The R-bot is embedded in the organization work environment, allowing unfettered access.
Dedicated intranet page
Compatible with internal live chat
Test our Regulatory and Compliance chatBOT
You can have an overview of R-bot at the following address:
• GDPR-bot: https://datascience-lab.sia-partners.com/rgpd-bot/
• Volcker-bot: https://datascience-lab.sia-partners.com/R-bot/
Enhance your applicants’ experience
Natural Language Processing at the service of HR processes
Free time for HR teams to focus on value-added tasks
Answers without human intervention to the recurring questions of the collaborators allows the HR teams to focus on the tasks with added value (complex requests, relationship with collaborators...)
With the help of neural networks, it is
now possible and common to design
chatbots capable of automatically interpreting natural language. Based on
an internal use case, the Sia Partners
DataScience team proposes a chatbot
capable of answering all of the main HR
Enhance the satisfaction of employees and candidates
Chatbots provide accurate, instant, and contextualized answers to questions
from employees or candidates. The level of satisfaction of chatbot users is
Develop a data-driven HR approach
Chatbots are used to collect contextualized data to know the questions and
expectations of collaborators and candidates; and thus to base decisions on
Combine the power
of APIs with our
Phrases the request
with the user
- Stores and
Requests an answer to
Thanks to its expertise in web development, Sia Partners has developed
its own chatbot interface. This web
interface is linked by an API key to an
automatic language processing engine,
based on a pre-trained neural network. A
knowledge base is built up, and links to
other APIs can be made to provide dynamic answers.
Therefore, the chatbot can understand
and answer questions according to a series of parameters, as well as the context
and the content found in the APIs to
which it is linked.
These bricks of technology have been
used for a number of robots, not just for
the HR sector, but many others.
Recruitment Chatbot – Use Cases
Tobias, the recruitment chatbot used internally at Sia Partners.
Thanks to the web interface developed
by sia, the chatbot is easily integrated
into any type of website.
The Data Science team has also made
chatbots for others sectors :
• Procurement Chatbot: answers questions of the suppliers on the specifications present in the database, sending
an email to the buyer in case of errors
in the specifications.
• GDPR Chatbot: answers all the standard questions about the new European Regulation and points to the right
interlocutor if needed.
Demo of the GDPR Chatbot
Our chatbots obviously formulate a text
response, but they are also able to provide rich content such as clickable links,
pictures, videos, or any type of document.
They are also able to alert an employee
when an interlocutor identifies a defect
or expresses the need to interact with a
human, for instance in the case of a particularly complex request.
Test our Recruitment chatBOT
By combining the work of our Recruitment Chatbot and the dataviz skills of our Datascience Team, you can test our bot on the
Detect uncommon behavior
Sectors and actors
looking for common
Energy & Utilities actors, Banking & Insurance companies or Transport companies are gathering huge amounts of
time series such as client consumption
or payment transactions.
The extraction of common behaviors
from these everyday life datasets can
help companies improve their data
quality, detect outliers and in the end increase their financial performance.
points with a machine
GENERAL OPEN DATA
Open data profiles of electrical consumption are used as basic time series for
analysis. It is representative of a nominal
client consumption behaviour.
Anomalies generally take the form of
positive (fraud) or negative (flexibility)
offset such as presented below:
Energy & Utilities
“ etect fraudulent activities
to protect both the bank and
Transport & Industry
“Detect outliers and fraud”
“ valuate a common
To face all these challenges, our Data
Science team has developed a bot to
simulate fraud / demand-response model-design detection from an electrical
consumption load curve.
MACHINE LEARNING FOR DATA
Sia Partners Data Science team is using
all its forecast algorithms skills to train
a robust model with the available data,
containing both regular behavior and
With an iterative multi-model approach,
atypical points are removed from the
training set of the forecast algorithm until the convergence of the model to the
anomalies on a
dataset: the bot will
The user can personalize the simulated
anomalies by choosing the number and
amplitude of the deformations. Visualize
the obtained curve on the graph directly,
which is used for model training.
Choose the tolerance threshold for anomaly detection and visualize the result
of the detection algorithm. Green zones
represents flexibility mechanisms (negative deformation) whereas red zones
Fraud Detection – Use Cases
Energy & Utilities
– Detecting Uncommon behavior
Characterizing fraud and flexibility
The anomaly detection is performed
from the difference between the model
curve and the real curve (containing
deformations). A tolerance threshold allows the user to define detection criteria
and all values above the threshold are
Thanks to an interactive graph, the
detected areas are easily visible to
users and the color code differentiates
between fraud (over-consumption) and
other mechanisms (under-consumption). The model is capable of accurately reconstructing artificially created
anomaly periods .
The top left graph displays an overview of the different stages of the iterative forecast
algorithm. It shows that :
• he model (blue) is converging to the
assumed common behaviour, represented by the original load curve (pink);
• he model quality is increasing with
the number of iterations;
• he model is robust enough to be
trained with a dataset containing abnormal points.
From these results, it is possible to evaluate the characteristics of each period
(starting date, length, amplitude, reliability of our evaluation) in order to better
dimension the impacts on the business.
Test our Fraud Detection BOT
You can have an overview of our application at the following link:
Using Deep Learning techniques
Recognition of objects
in satellite images
using a pre-trained
to achieve the best
Visual recognition of objects in satellite-based images is now possible
thanks to deep learning algorithms.
For our clients, this means that objects
such as houses, stadiums or parking
lots can be detected automatically.
Such data can be leveraged in order to
create value. These are some of the application domains :
Use of open data
and construction of
Satellite images can be acquired in real
time by private satellite image providers
or scraped from services such as Google Maps or Bing Maps. The data is then
enriched with the annotations needed to
run the training algorithm.
The algorithms are executed on servers
equipped with NVIDIA Tesla GPUs, which
ensure a minimal training time for the
deep learning model.
We use the Deep Learning framework
Tensorflow, which enables us to keep our
code up-to-date with the best-performing
Convolution Neural Network models.
The trained model is then exposed to the
client via a web API and a web application.
The user sends the image and the model
identifies the objects to be recognized.
Counting objects in a given zone
Soil and vegetation recognition
Feature extraction from given objects
In order to be able to realize these tasks,
Sia Partners’ Data Science team has
created a bot which enables users to recognize objects in satellite images.
Using Tensorflow, our Datascientists finetune a pre-trained Deep Learning model
such as ResNet-101 or Inception-ResNet-v2 in order to obtain a model capable
of recognizing the required objects.
MOTOR INSURANCE PRICING
Scoring the risk of a car ride
Enhancing the motor
Leveraging open data to build a risk score
VARIOUS AVAILABLE DATA
Road networks are a key factor to explain
motor risk exposure.
TRANSFORMED WITH MACHINE LEARNING TECHNIQUES
The public database of car accidents provides relevant information on risk geography.
Multiple use cases
Integrate this score as a new input to the existing model to improve its performance.
Sia Partners has developed a user-friendly
robot that exploits this data to assess the
risk of a car ride.
Use the most frequent ride (from home to work) to increase price segmentation.
PAY HOW YOU DRIVE
Synergize this score with telematics covers whose price depends on real-time collected
Test our Motor Insurance Pricing BOT
By combining the work of our Motor Insurance Pricing BOT and the
dataviz skills of our Datascience Team, you can now measure and visualize the risk of any car ride.
Occupancy rate forecast
Occupancy rate: a key
indicator for parking
The occupancy rate of car parks and parking areas is a key factor in parking management in urban areas.
Being able to anticipate the parking occupancy rate is therefore a major asset
in parking management, as it helps in the
Dynamically adjusting pricing
Anticipating the periods
Visualization of the availability of car parks,
associated with other factors
GRAPHICS ON THE AVAILABILITY
OF CAR PARKS...
The historical and projected occupancy
rates are displayed for a selection of car
parks in Île-de-France. Each car park is
also represented geographically for better visual understanding.
Dygraph technology is used to offer a better user experience on the app: easy handling of the graphs (selection and zooming on timeframes), aesthetic graphs.
... ASSOCIATED WITH
… and many others!
Use of open data and construction of forecast
THE DATA SCRAPPED...
Anticipating management costs
(resources, energy, ...)
Rethinking the levers of profitability of car parks (advertising,
providing consumer goods, ...)
To help with to all these issues, Sia
Partners' Data Science team has created
a robot which enables users to visualize
the occupancy rates’ forecasts of a selection of car parks.
... FEEDS THE MODEL
Sia Partners’ robot regularly recovers data
available on the internet:
• Daily weather data
• Daily carpooling data
• Events’ data on a weekly basis
• he occupancy rate of car parks
every 15 minutes
Every hour and for every car park, the
robot calculates estimated occupancy
rates according to four models:
• Daily copy
• Copy on a weekly basis
• Regression on the last weekly values
• Use of neural networks
Parking Availability – Use Cases
The main screen of the application displays a map:
• Modelled» car parks (those for which we
collect occupancy data) are highlighted;
• arpooling spots and unmodeled car
parks are also represented;
• colour code makes it easier to recoA
gnize the busy areas in terms of number
The visualization of the graph allows the user to take a look at
the historic and forecast occupancy rates. Thanks to the use of
the Dygraph package, the user may notably:
• asily select his study timeframe, via the selector located beE
low the curve or directly by selecting the data on the corresponding curve;
• iew the values of occupancy rate of the car parks every 15
minutes, by flying over the curve with the cursor of his mouse.
Note that weather and event data are displayed on the main
screen, below the graphic, to allow a more complete analysis.
Test our Parking Availability BOT
By combining the work of our Parking Availability BOT and the dataviz
skills of our Datascience Team, you can now have a look at the occupancy rate forecast for several car parks in Île-de-France.
65% Business Transformation
15% IT & Digital Strategy
5% Data Science
OUR INNOVATIVE ECOSYSTEM
Design Thinking Lab
DataSets & DataLab
Data Science Showroom
APIs & Consulting Bots
Voice Recognition/Virtual Assistants
Taxonomy & Ontology
Conversational User Interfaces
Digital Due Diligence
Digital Trends Observatory
Digital Assessment & Strategy
New ways of working
POC to industrialization
Students Contests | Hackathon
Open Source Thought Leadership
Tel : + 33 6 69 77 02 11
Tel : + 33 6 82 41 48 43
ABOUT SIA PARTNERS
Founded in 1999, Sia Partners is an independent global management consulting firm and pioneer of Consulting 4.0 with over 1,100
consultants and an annual turnover of USD 200 million. The Group has 20 offices in 15 countries. Through unparalleled industry
expertise, Sia Partners delivers superior value and tangible results for its clients. True to its innovative approach, Sia Partners
explores the possibilities offered by Artificial Intelligence, invests in data science and develops consulting bots. Sia Partners is a
global partnership wholly owned by its executives.
Al Gaith Tower #857
PO Box 54605
Abu Dhabi – UAE
Barbara Strozzilaan 101
1083 HN Amsterdam –
Av Henri Jasparlaan, 128
1060 Brussels – Belgium
46, Boulevard Adbellatif Ben
Kaddour, Racine – Casablanca
20000 - Morocco
101 S. Tryon Street, 27th Floor,
Charlotte, NC 28280, USA
Al Fardan Office Tower #827
PO Box 31316, Doha – Qatar
Shatha Tower office #2115
Dubai Media City
PO Box 502665, Dubai – UAE
23/F, The Southland Building
48 Connaught Road Central
Central – Hong Kong
800 Town and Country Blvd
Houston TX 77024
36 - 38 Hatton Garden, London,
EC1N 8EB – United Kingdom
7 rue Robert Stumper
3 rue du Président Carnot
69002 Lyon – France
For more information on Sia Partners: www.sia-partners.com
Via Vincenzo Gioberti 8
20123 Milano – Italy
304 - 19 Rue le Royer Ouest
Montreal, Quebec, Canada, H2Y
137 Market Street #10-02 Grace
Marunouchi Trust Tower-Main
1-8-3 Marunouchi, Chiyoda-ku
Tokyo 100-0005 Japan
40 Rector Street, Suite 1111
New York, NY 10006 – USA
12 rue Magellan
75008 Paris – France
Anas Ibn Malik Rd.
Al Malqa, PO Box 19970
Riyadh 11445 – KSA
Via Quattro Fontane 116
00184 Roma – Italy
Follow us on LinkedIn
Fleepit Digital © 2020