We have an authorship program, where financial advisors across the country license our manuscript content from a book we published and work with our publishing partner to customize it for themselves. We offer these advisors/authors to submit a "distribution list." This list is 500 401(k) plan prospects plus their client list (these prospects are businesses/companies). We would like to prevent advisors in the authorship program from prospecting to the same companies. We need a partner to archive these lists and manage the process which would require cross checking each advisors lists for duplicates. This would be an ongoing partnership, as new advisors come on board to become authors, we need to let them know if anyone in their distribution list is already on someone else in the program's list, which would mean they can't prospect to them using their book.

The end deliverable to us would a centralized database with a simple front-end. Essentially we are looking for an Expert, who can build a smart central database for us to house the advisor's mailing list data. This database needs to automatically detect duplicate accounts/plans once the author upload his/her data. We are looking for a smart database with rules that allow the author to be notified if there are duplicate accounts and to not contact those accounts.

We are open to any technology, idea and methodology. We also prefer to have the Expert be able to meet during U.S. Eastern Time Zone business hours. 

In your proposal, please provide the estimated amount of hours this would take.

Overview

We are a marketing technology and media buying company buying and deploying a host of media and tactics (Digital, Traditional and Social) across various markets in the United States. As such, we are collecting a lot of data otherwise not typically aggregated in one platform.

Problem

We are trying to build a predictive model that we can apply to each market we place advertising in to optimize future marketing investments and as a result, increase ROI.

We want to:

- Balance short-term marketing and promotion tactics with long-term brand building needs

- Understand marketing ROI for each offline and online media channel, campaign and execution (i.e., search vs. circular vs. TV)

- Optimize allocation of traditional media vs. digital media and determine the synergies between the two with marketing mix modeling

- Quantify the value and impact of emerging/new digital media (Facebook, Groupon, Foursquare, mobile apps, etc.) with a personalized digital marketing strategy

- Lock into the right marketing mix by region, country and go-to-market channel

- Determine which media vehicles and campaigns are most effective at driving revenue, profits, share and consumer segments

- Quantify the ROI of improving marketing effectiveness in terms of sales, profits, share and target consumer growth

Expertise Required

We are seeing someone authorized to work in the United States who has had a track-record and significant experience in the above. And if this pans out, is open to the idea of longer-term relationship.

Data Sources at Our Disposal / Current Technology Stack

We have a host of database developers that can assist with getting you what we need, either from outside sources to augment the data or of course, inside sources based on the data we are generating.

Our technology stack relevant to this project is: 

Postgres, Apache Tomcat, LogiAnalytics Java engine

What are we looking for?

Someone to:

- Pointing to a successful track record of similar projects and referrals, help us save time and effort by giving us key instructions on how to set this project up for success.

- Analyze the data we have.

- Suggest additional data we should be capturing or third-party sourcing

- Find patterns and unlock value in the data beyond the obvious, helping us report back on key findings.

- Build predictive models as a result of key learnings.

- Supply our technical team with models to build into our product and deploy to our Private Cloud-Based Application. NOTE WE ARE NOT EXPECTING THE CONSULTANT TO DO THIS WORK, just provide us the specifications to help build this into our platform.

Samples data files and fields will be provided upon execution of an NDA after initial proposals are submitted. For all intents and purposes, assume we have all the data necessary to derive value out of this project.

Overview

We are a marketing technology company printing and mailing a lot of direct mail for our SMB customers. As such, we are collecting a lot of data otherwise not typically aggregated in one platform, including unique response data tied to each direct mail piece.

We have a data-set with over 1,000 direct mail orders, perhaps millions of recipients. We have response data (call-tracking data) for each order monitoring unique calls. We also have a number of attributes on each order - i.e. the creative used, the offer available, the day it dropped, the geographic area it dropped to, the demographic make-up of the ZIP Codes, the type of mail, etc. We also may be able to access lists of actual customers.

2 Problems to Solve

Problem #1

We would like to build specific data models around core product offerings and promotions that we know will optimize targeting and list purchase techniques for direct mail and therefore maximize ROI on each campaign. 

Problem #2

Other than the list targeting component of direct mail, there are many other factors that affect ROI. We'd like to figure out all the factors that influence outcomes to make recommendations to our clients on how to decide on creative, offers and other mailing techniques based on the audience being targeted to maximize ROI.

Expertise Required

We are seeing someone authorized to work in the United States who has had a track-record and significant experience in the above. And if this pans out, is open to the idea of longer-term relationship.

Data Sources at Our Disposal / Current Technology Stack

We have a host of database developers that can assist with getting you what we need, either from outside sources to augment the data or of course, inside sources based on the data we are generating.

Our technology stack relevant to this project is: 

Postgres, Apache Tomcat, LogiAnalytics Java engine

What are we looking for?

Someone to:

- Pointing to a successful track record of similar projects and referrals, help us save time and effort by giving us key instructions on how to set this project up for success.

- Analyze the data we have.

- Suggest additional data we should be capturing or third-party sourcing

- Find patterns and unlock value in the data beyond the obvious, helping us report back on key findings.

- Build predictive models as a result of key learnings that can help us purchase mailing list aquisition data to maximize ROI.

- Supply our technical team with models to build into our product and deploy to our Private Cloud-Based Application. NOTE WE ARE NOT EXPECTING THE CONSULTANT TO DO THIS WORK, just provide us the specifications to help build this into our platform.

Samples data files and fields will be provided upon execution of an NDA after initial proposals are submitted. For all intents and purposes, assume we have all the data necessary to derive value out of this project.

Keurig has a data set of coffee brewing activity of a consumer research panel.  We need help analyzing these individual brew histories of ~1,000 Keurig users over an ~6 month period to determine the average “calibration period” (# of days of brewing data) needed to accurately predict long-term brewing frequency (avg. # of pods brewed per day over the entire 6-month period) with high-levels of confidence (90%+).

In total, there are 250,000-300,000 data points across these 1,000 users and the data is housed in an Excel file.

We need the results in 1 week from the start of the project.

We are an owner of an online point reward website in Japan, which lets its members earn points in exchange for purchasing/ registering through our advertiser’s websites. A percentage of the advertisers’ commission is used to pay a reward to our members.

Currently, most of the traffics to the reward website are generated through e-mail newsletters. We would like an expert to analyze our members’ data (profile and transactional data), and propose us the optimal segmentation, in order to increase conversion. Using the segmentation, we could send targeting e-mails, realizing a higher conversion.

Available data for analysis will be shared during interview stage. 

-Profile data of the top 340K members (CSV)

-Purchase data (around 640K transactional data)(CSV)

For one of the our clients we are looking at developing a PRICE ELASTICITY tool, ideally in EXCEL, that can be shared with their Sales Leaders in the marekts so that they can calculate their local price elasticity.

• The client is a Food & Beverage company
• The tool will be deployed to the market to standardize the way Price Elasticity is calculated
• Today's price elasticity is calculated sporadically and inconsitently across markets
• The tool needs to be in a format that can be shared with the market given they don't have access to softwares like Tableau or similar and that they will have restrictions to do any cloud based deployment. Alternative could be to have the tool online but it would need to be deloyed within their intranet.
• Attached is a sample of their data / metrics

Please list your questions in your proposal and I will respond accordingly.

We are a Silicon Valley healthcare startup that’s using advanced data science to solve tough problems in healthcare operations. We are looking for a senior data scientist for a on-site in Santa Clara, CA on a six-month contract that can lead to a full-time role.  You must have proficiency in R and Python; linear programming; and possess expertise in machine learning.

The Senior Data Scientist role involves working on all stages of the data science pipeline, from acquiring and munging data, selecting appropriate models and algorithms and/or deriving custom algorithms, testing and evaluating these algorithms and models, and incorporating them into a commercial product. She/He will work with a team of Data Scientists to create bleeding edge analytic technology.

Key Responsibilities

• Analyze various data sets and build sophisticated mathematical/statistical models 
• Design and optimize algorithms to achieve the best solutions 
• Develop innovative strategies, processes, and best practices in several functional areas including operations, customer satisfaction, and marketing
• Drives the execution of multiple business plans and projects  
• Help deliver complete solutions to various industries including consumer goods, retail, healthcare, and technology

Qualifications & Experience

• Strong quantitative and analytical skills with an advanced degree in a STEM discipline (PhD preferred) 
• Experience using at least two of the following: R, Python, C, C++, SQL, Java
• Experience analyzing data sets, building mathematical/statistical models and/or optimization algorithms 
• Ability to communicate complex quantitative analysis in a clear, precise, and actionable manner 
• Ability to work collaboratively and independently

Only Candidates within the United States may apply. You must be willing to relocate to Santa Clara, CA.

We are one of the top 10 e-commerce retailers in the world and are looking for a Spark Engineer with Kafka and Hadoop experience.  Here is our system topology.

• Real time application events (Web requests metrics - CPU, Memory, Response Times, Transaction Count) are published to Kafka messaging queue.
• Storm acts as a consumer of those real time events from Kafka queue.
• The Storm topology processes the data and writes it to HBase.
• REST API(Jersey).Service Layer running on a separate JBoss VM is being used to query raw data from HBase and render it to the user interface.
• Hortonworks distribution – HDP 2.4, Spark 1.6
• Strong understanding of HBase architecutre, capacity sizing

We need to have a real time / dynamic aggregation on the raw data available in HBase.

We are looking for an expert who has experience developing Spark data streaming in near realtime (< 5 seconds) and have a good understanding of Hadoop architecture and its components. Please respond with your previous experience developing realtime systems using Spark, Kafka and Hadoop.

This is a two-week project, involves working remotely and would need to start as soon as possible.

About Us

We are a company that produces marketing materials through mass customization and web-to-print systems. We operate globally with 6 main markets and offer services to help small businesses create an identity for their company.

 

Problem Statement

Today, we have the capability to recommend personalized products through specific merchandising placements on our ecommerce site. We are working to update our strategy and models across our global ecommerce platform. The scope of this project is for two different locations on our ecommerce site, with differing strategies, that we want to build models to solve for.

 

From a business perspective, we want to build revenue-driving CrossSell recommendation models that:

•       Provides our customers with relevant products that satisfy, surprise and delight - at the right time

•       Brings awareness of product offering and inspiration with our depth of designs

•       Is easily, accurately and flexibly managed

 

From an analytical perspective, we want these models to:

•       Ease of Optimization: Current thinking is that the models should be self-learning. That being said, we are open to differing opinions and alternative ways to achieve similar performance results. The main goal is to reduce manual model rebuild and calibration.

•       Scalability: The system should be able to accept new products and start optimizing with current recommendations. Again, we are looking for advice and recommendations on how best to achieve this.

•       Integrate with existing Hadoop-based Decision Engine platform for developing and deploying models

 

Success metrics could include:

•       Take Rate = Items Ordered/Items Offered

•       Engagement Rate = 1+ Items Ordered/Visits to CrossSell page

•       Bookings, Gross Margin

•       Improvements in Net Promoter Scores (long-term)

•       Incrementality; increase in orders or increase in items per order

 

Customer Experience

When a customer visits www.vistaprint.com and selects a product to personalize they go through a flow that has them customize their design (see Appendix A), select options for substrate and quantity and then they are shown a ‘Matching’ page that is our CrossSell experience in the customer journey that showcases their selected design on multiple other products (see Appendix B). This is one of the merchandising locations that we need to build a new recommendation engine for.

 

If you are a customer with an account, or have purchased before, you will have a username and password. Upon entering your credentials you are typically directed to the ‘Returning Customer Homepage’. The top half is dedicated to links for account maintenance, order history and saved or in-progress projects. The bottom half of the page is where we showcase our ‘Recommendations for You’ section that renders your previous designs on additional products (see Appendix C). The desire here is to showcase new or new to the customer products to increase awareness and encourage engagement and purchase. This is the location of the second model that we need to build.

 

To render this type of customer experience there are multiple models and services called. To simplify it;

• There is a model that tells the site what product to show (this is what we are focusing on rebuilding)
• There is a matching (imagery) engine that determines the best ‘match’ to the customers selected design and then renders it on the product. This is what the customer sees (see Appendix B)
• Then a pricing service determines the price to display, taking in to considering the customers referring domain and current promotional activity on the site.

 

Data Available

·         Transactional data: Which includes everything related to orders that customer have placed in the past. We can aggregate this data to any level necessary for modeling.

·         Basket data: Many times our customers add items to their carts that do not end up in an order. The basket data contains product category of last 30 days and current item in carts. The data includes only binary data for whether a product is / was in the cart of not.

·         Site browsing data: Similarly to transactional data, we have all the information grouped by product category and we have aggregations at the following levels: last session (whenever it was), last 7 days and between 7 and 30 days. For each one, we have number of navigations to that product and click information to specific products. We also have access to Tealium data and can build additional variables as needed.

·         Customer segmentation: We have 5 different customer segmentations with 5 levels at most in each. These customers’ segmentations describe visual patterns on what customers are (Consumer vs Business).

·         Product data: We have limited product attribute data currently available but know that there is an opportunity to create data and have plans to explore this as a way to recommend products new to our assortment.

·         Response data: We have access to historical data pertaining to the current CrossSell placements and customer engagement.

 

Expertise Requirements

We are looking to resource this project with someone that can serve as an end-to-end advisor for this project. As a consultant, your job would be to consult on the statistical/modeling approach, architecture of the system and execution. This job is for someone that can develop a good partnership as we will not only implement the system, but we need to understand the pros / cons of any approach as well as future challenge as it related to data management, score computation, site experience impact etc.

 

Knowledge of the latest machine learning algorithms for recommendation engines is desired but not a requirement. As stated above, we think this is the direction we should head but would like to explore all options.

 

Other Contract Details

Timeline: Internal teams at Vistaprint began work in May 2016 to collect, process and prepare the data for modeling exercises. This is expected to be ready for use by mid-June 2016.

Location preference: Majority of the team is located in Waltham, MA with one Decision Scientist in London. We’d prefer that we partner with someone that is able to co-locate with us in our Waltham office.

 

Questions that we have

·         What methodology for modeling would you recommend for our use cases? We’d like to understand the computational complexity and scaling pros/cons.

·         How would you allow new products to start being recommended?

·         What technology or platforms do you have experience with?

·         How do you make sure the recommendation is generating incremental responses and not only targeting people with high likelihood of buying?

·         What could we do to set ourselves up for success in scaling? From a couple thousand SKUs to hundreds of thousands of SKUs?

·         What have we not asked that we should be thinking about?

Gulf believes that advanced data mining techniques can be used to create a truly unique and differentiating user experience at the station, and intend to develop a system for handling the identification, payments and data intelligence for retail customers. This project is one of several which are being offered through Experfy which, in the aggregate, will represent the initial version of our customer analysis solution.

Our system has been designed to emphasize the following (in decreasing order of priority):

• security
• reliability
• speed to market
• flexibility for future enhancements

To support these objectives, the system has been designed to support both batch processing and stream processing using an architecture similar to the well known “Lambda Architecture” pattern.

In this component of the solution, we are focusing on the batch processing components of the system. The emphasis in this project is on the development of ETL processing to support both our business intelligence function as well as our promotional campaign management. This component does not contain a significant element of machine learning.

Scope of Effort

We are looking for a developer to develop the batch processing components of our system. We have developed a reference architecture consisting of a combine real-time and non-real-time processing flows (see https://www.sugarsync.com/pf/D6703166_07623628_708603) but expect that the developer will build upon this design as appropriate. Our emphasis has been to develop and deploy a fieldable system as quickly as possible, knowing that we will incorporate additional functionality as we grow. At the same time, we wish to reduce the need to maintain a large in-house IT support staff. As a result, the architecture has been designed to heavily leverage Amazon Web Services. Our expectation is that the bulk of the development associated with this portion of the architecture will incorporate some combination of AWS Kinesis, Lambda, Elastic Map Reduce, Redshift and other services for communications (e.g. SNS or SES) as well as some form of visualization / querying tool. Other projects will focus on the analytics and machine learning aspects of the project.

At a high level, this project will result in a system which accomplished the following:

• perform a regularly scheduled ETL process for collecting and transforming previously collected event data into a data warehouse suitable for supporting business intelligence functions
• manage the data components of our customer loyalty program, including the creation of notifications requesting reviews of recent customer experience
• collect event data through our RESTful API component
• disseminate these events to processing elements using a streaming system
• store and process these events to create a customer profile and support the desired in-station user experience
• a critical component of the in-station user experience is the identification of marketing campaigns relevant to the current customer
• provide various forms of notification to the customer and local sales persons
• support a combination of pre-defined and ad hoc queries against the data warehouse

The project will include the following development efforts:

• a customer facing application targeted for Android phones
• a browser based desktop application, including a tool for defining and managing promotional campaigns
• cloud based processing infrastructure
• cloud based processing infrastructure
• an appropriate business intelligence tool. This visualization and querying tool could be constructed using with existing tools (e.g. Tableau), through the AWS hosted system, QuickSite, or perhaps using an approach based upon custom development, e.g. D3.
• cloud based processing infrastructure

In addition to the user facing applications, the system being developed will also need to be integrated with the following existing, external systems:

• MAC address sniffers in the stations
• License plate readers in the stations
• Payment processing systems
• Government regulatory agency systems

More details are provided in the accompanying requirements document.

We expect that the developer for this project will need to coordinate closely with the developer of our analytics and machine learning system to ensure that the overall system satisfies the client requirements.

NOTE: If you want to take on only parts of this project, please feel free to submit a proposal.

Proposal Requirements

In your proposal, please provide:

1. previous work that you have done that is relevant;
2. how you would approach this development exercise; and
3. estimated hours and budget.