We are an online travel company and are looking at fraud detection and fraud prevention analytics and intelligence from inside and outside the organization. What this implies is collecting, processing and analyzing all characteristics of a transaction and focusing on people, process and technology needed to improve fraud rates.

We would like an expert to iterate through fraud pattern changes, perform multi variable analytics, detect anomalies using strong data profiling, study fraud indicators, derived from the current transaction attributes as well as cardholder’s historical activities. Over time, we would like to build models using algorithms and machine learning to provide more predictive capabilities that can identify and mitigate fraud.

Our intent is to make as many systematic decisions as possible in order to lower overall overhead costs and ensure optimal customer experience and continuous cyber security enhancements.

The universal problem is how to quickly determine the root cause of incidents and then contain and remediate them. Once this is completed, the goal is to return intelligence from the analysis back into the system for proactive diagnostics and mitigation for continuous cyber security improvement

Expertise Required:

Statistics Ph.D. or related ML and classification methods (Multiclass SVM, MNLogit, Bayesian Belief Networks) Multiple imputation, sampling methods, factor analysis, PCA, Distributed processing , neural network technologies, GBM, data profiling and accuracy calculations, data standardization, root cause analysis, breach detection, fraud scoring,  Fraud Prevention Technologies – AVS, BIN,CVM,etc. data visualizations and master data management.

Contract period:

We are open to discussion based on your previous experience addresses similar project needs.

Location Preference:

The engagement may require some onsite presence at our New York City HQ to work and interact with our teams.

We are looking to hire a machine language engineer to develop algorithms based on health care data which can generate automated treatment protocols given a definitive diagnosis.

Aims

The aim of this study is to explore whether a computer - by means of a machine learning algorithm - can generate a treatment protocol given a definitive diagnosis for a disease that is complex to treat. This is not an attempt at automating diagnosis, but given a definitive diagnosis, predicting a treatment plan. The study will further compare the level of accuracy that can be attained by the algorithm, with an initial benchmark of matching the capability to be on par with that of a first year resident.  The first disease that will be explored for this study is Rheumatoid Arthritis.

 

As data on RA patients and the treatment plans that are designed by doctors for each patient is gathered, it will be handed over to machine learning engineers who will be responsible for developing the initial algorithm. The initial data points and those collected subsequently will be fed into the algorithm to teach it how to generate treatment protocols. Once a critical mass of data points is reached, these automated protocols will be validated by doctors. The validation or amendments will also need to be fed into the algorithm to train it to be more accurate. Over the next few months, we plan to have a sufficiently robust algorithm that can not only replicate the efforts of a first year resident but will also be able to output an explanation supporting that protocol. The ability to provide an explanation is a key component as a doctor needs to be able to justify signing off on any automatically generated protocol.

For a more detail descrtiption of project please view attachement. 

We are transforming three thousand full-service gas stations for sensor-based data collection to enable real-time personalization and customer analytics.  We are looking for an expert to put together an architecture, and a detailed requirements document with budget to implement a data platform and analytics that will serve 3,000 gas stations with 50 customers per hour per station. You must have experience preparing detail budgets and requirements for a large project that involves building a data platform and customer analytics. Experience with open source data platforms like CDAP is a plus.

User Experience

Each salesman would have a mobile or web app on an Android Tablet to be informed of useful customer data and provide additional information.The customer would have downloaded a driver’s mobile app and register himself or herself with a payment method and his or her vehicle’s plate number.

1. The customer arrives to the station and is identified when he stops at the pump by reading his car’s plates. In a second step, he is also soft-authenticated by verifying if his mobile device’s MAC address is connected to the station’s Wi-Fi antenna at the moment.

2. The salesperson’s tablet would provide customer insights that would allow for a better experience and opportunities for upselling. It would also show whether the customer has automatic payment activated, provided complete invoicing information, and is eligible for a coupon or any other loyalty offer.

3. Then, the gas recharge process runs as usual, creating an entry with the details of the process, such as product, amount, location, timestamp, user data, etc. This data is obtained by mixing user data and station’s software data in a local server.

4. When the recharging process ends, the payment process may follow one of the following scenarios:

• Auto-Payment: Users who has Gulf’s prepaid e-card do not have to do anything when auto-payment is activated, when plate’s have been read correctly or when the customer's mobile device has been detected at the station.
• On-App Payment: Users with Gulf mobile app can opt to pay with his registered payment methods: (1) Gulf prepaid e-card; (2) Visa Card-On-File (with an extra convenience fee); (3) PayPal (with an extra convenience fee); (4) Other third parties’ e-cards (to be defined).
• Traditional Payment: Users with or without Gulf’s app can also opt for traditional payment with cash, paper coupons, debit card or credit card. In these scenarios, the salesman should inform on his app.

5. The sales person would get a notification when the payment is approved and the final payment data is sent to the clod server and the invoicing process begins by sending required info to facturador.com service.

6. Later, the customer would be required to grade the experience to get his loyalty points and a notification when his invoice’s ready.

Business Requirements

It is crucial to design a disruptive, flexible and scalable platform with high availability that fulfills the following business requirements:

1. Non-sensible data integration: All customer interactions, both purchasing, visiting or interaction with any of our engagement and loyalty proposals, would be cloud-stored, centralized and available for further analysis. External data sources may also be added.

2. Sensible customer data: User private information, such as vehicle’s plate, MAC addresses, hashed passwords or biometrics and other should be safely stored and available only by certain services.

3. Centralized cloud app: It will centralize and process authentications, queries, transactions, fuel volumetric data, automatic invoicing and the payment platform.

4. Local service station app and buffer database: A local server would be running a local app to ensure the service 24/7 regardless of internet’s signal intermittence. This app would interact with the following services:

• Mobile salesman app
• Service Station’s control software
• Point-of-Sale
• Centralized Cloud app
• Centralized Cloud Database
• Identification and authentication platforms

5. Driver’s mobile app: A wallet app with notification capabilities will work as the main customer interface. There, the customer will register and create his prepaid account, link more payment methods, fill his invoicing data and interact with Gulf’s gamification scheme and loyalty program.

6. Salesmen tablet app: This app will show useful customer insights and his availability for auto-payment, invoicing and other; sales people may also add additional customer preferences. This app should manage two different profiles: admin and user.

7. Servicing platform: Customers may have access to a FAQ site with an online chat service integrated to manage questions and complains.

8. Data analytics: All non-sensible data is subjected to be aggregated and analyzed for commercial intelligence purposes. Also, some reports to energy and fiscal authorities will be processed and generated from the whole aggregated data.

9. Loyalty points platform: Users will be rewarded with Gulf’s Power Points for visiting us (check-in), purchases based on the payment method, social network’s interactions and referrals. Those point would be used to acquire coupons (for Gulf or our allies) or branded merchandising on an e-platform.

10. Gamification platform: In a second engagement platform, the customer will earn Experience Points (ExP), and badges to advance through levels.

11. Campaign manager: It’s a web app for Gulf to upload certain geo-based campaigns:

• Earn extra points
• New and last minute coupons
• New branded merchandising
• Any other push, SMS or email notification

We have additional details for each of the eleven point above that we will share with the Experfy expert who is hired for the project.

We would like to begin the project ASAP and complete it within two weeks if possible. Please tell about your background and approach; what makes you qualified to work on a roadmap and requirements document for this project; your availability to work and what kind of support you require from our stakeholders.

If you have put together a requirements document for a different project in the past, even if it a completely unrelated project, it would be helpful for us to see it.  It would help us determine how detailed your plans are and if you have experience with budgeting.

We are the fourth-largest radio company in the United States, owning 130 radio stations across 30 media markets.  We want to unlock the value of our first party audience data to better manage programming and advertising sales decisions, while reducing dependency on Nielsen 3rd party data.

Ad buying community is moving toward programmatic buying platforms which value targeting by audience segments that are more sophisticated than historically offered by a Nielsen/Scarborough Ranker.

We are looking for an expert with business experience in assessing the value of big data, and building a business plan for positioning our data as a strategic asset.

Data Sources

Our data sources are audience data from first party sources (registration/behavioral), 3rd party audience data sources (Nielsen, Scarborough and Quantcast). We also have lots of data as relates to our broadcast ad trafficking schedules & pricing.

Deliverable

The deliverable is a strategy whitepaper for our Senior Team that defines the landscape and recommends two to three paths that we might pursue in a marketplace now driven by Audience Insights and programmatic buying.

This position will lead and manage analytical work designed to solve key data challenges across the enterprise; lead process improvement activities regarding data that support all business units; gather requirements from key end?users and translate them into an effective data system design, while considering and anticipating organizational impact. Accountable for Data architecture for large capital and departmental projects, System Strategy, Business Technology Strategy and vision to meet Enterprise Architecture goals. 

Responsibilities: 

• Create and refine data solutions for complex requirements. 
• Determine how data should be structured, managed and maintained across  the solutions. 
• Consider security and data privacy requirements and other requirements on a design by design basis. 
• Partner with subject matter experts to identify and collect detail data requirements. 
• Participate in process flow analysis and process redesign, as needed. 
• Share knowledge and experience to enhance the technical capabilities of peers and build prospective opportunities. 
• Manage work in accordance with Horizon ePMO, SDLC, and release management processes. 
• Partner with the Technical, Solution and/or Enterprise Architect to produce a technical specification for purchased solutions, custom development solutions and systems integration requirements. 
• Identify and propose specific strategies, initiatives, and remedies necessary to align technology infrastructure with corporate and divisional objectives. 
• Understanding in network design, cloud, mobility, with a focus on security, resiliency, availability, and performance. 
• Design and build data reference models. 
• Must demonstrate good judgment and pragmatic approach to delivering software that optimizes architecture activities across company needs, business constraints and technological realities. 
• Participate and lead customer meetings as necessary. 
• Participate in internal projects as required. 

Qualifications: Education/Experience: 

• B.S. degree in Computer Science, Software Engineering, MIS or equivalent preferred. 
• Overall 15 years professional technology experience. 
• Minimum 8?10 years of detail design and development experience. 
• Minimum 5 year’s experience in health insurance industry, preferred. 

Knowledge: 

• Strong business knowledge, coupled with understanding of data management technology used to manage data (ETL, SQL, Databases, Data Quality). 
• Strong knowledge of BI and analytic tools, preferably SAS and Cognos. 
• Experience with DB2, Oracle and SQL Server, and knowledge of using MS Access and Excel for data extraction/manipulation. 
• Strong understanding of data modeling, data integration and data analysis. 
• A general understanding of the metadata requirements for analysis results and for datasets. 
• Knowledge in web?based systems architecture, service?based architecture, enterprise application architecture. 
• Knowledge and experience using established middleware platform. 
• Strong knowledge of PM methodologies, tools & practices, preferred. 
• Experience in common frameworks such as Zachman, TOGAF, DoDAF and various data design and modeling tools (Erwin, etc), preferred. 

Skills and Abilities: 

• Strong organizational skills, analytical, adept at working in a team environment, and the ability to manage multiple priorities and deadlines. 
• Strong leadership, facilitation, negotiation, and mentoring and team building skills. 
• Strong critical thinking skills, ability to translate concepts into execution tactics. 
• Strong PC skills and expertise in MS?Office suite including MS?PowePoint and Visio. 
• Aptitude for data standards and data standardization. 
• Ability to express complex technical concepts effectively, both verbally and in writing, to diverse groups of people. 
• Ability to demonstrate good judgment and pragmatic approach to delivering software that optimizes architecture activities across company needs, business constraints and technological realities. 
• Ability to effectively interact and influence all levels of management. 
• Ability to talk through concepts with a client. 
• Ability to thrive in a fast past environment. 
• Ability to develop and maintain strong working relationships with key stakeholders.

Location

The position is based in Newark, NJ and is part of a larger consulting engagement. All work is to be performed on-site.

Proposal

In your proposal, please state why you think you are a good fit, also attach a copy of your resume in MS Word format.

Project is continuation of another project and will be awarded to same Expert. 

Project is part of a continuation of a previous project and will be awarded to same Expert. 

Create a web-based application to provide Poolsure with estimates on pool usage. The application should also be such that it can serve forecasts through an API so that Poolsure can use them across the organization if needed. In summary the application would entail

• A web interface for basic data management tasks
• An API to allow access to predictions to be used in other applications
• Integration with Netsuite to get Poolsure’s data automatically in
• Integration with NOAA to continuously get get weather data
• Logic to compute and maintain predictive models
• Data base schema to hold necessary information

The application would be hosted in the cloud.

Hello,

We would be interested in soliciting interests from experts who have working knowledge of graph management databases, precisely Neo4j and have worked on building a Master data management solution using Neo4j. 

We need help to build the graph - MDM solution in-house that we wish to sell to our clients in the Pharma and Life sciences industry. Prior experience in MDM and not limited only to the US Market is mandatory as we have a very short turn around time for project delivery and need to start with prototyping a solution as quickly as possible.

The MDM solution will be hosted on the Amazon cloud and we will need help to initially build the graph data model, import sample data to build the nodes and relationships within the data set and then write Cypher queries to align with the business requirements of our client. For the prototype we would be interested in connecting to graph visualisation tool - Gephi or Linkurious to display the data connections in a visual format. 

Interested parties need to respond with details of relevant experience both in building graph databases & graph visualisation and MDM. References to prior work in this area will be highly appreciated. In addition, while providing a price estimate we expect to recieve a formal response to include but not limited to, the requirement gathering mechanism, the role & responsibilities of the expert and other parties in the engagement, ownership and transfer of intellectual property, key project milestones and deliverables at each milestone.

Thank you for your time.

Best, 

Overview

We are a Commercial Real Estate firm that specializes in all areas of commercial property management.  The core services include sales, leasing and property management.  Accordingly, the two divisions in the business are:

1.     Sales and leasing – Sales and leasing of  new listings and therefore these properties do not relate to the firm’s managed properties.

2.     Property Management – We manage many properties on behalf of our clients, which from time to time become available for sale or lease.  

Accordingly, it is important to measure the sales and leasing revenue derived from non-managed properties as well as sales and leasing revenue from managed properties separately.  It is equally important to measure sales revenue and leasing revenue separately.  Accordingly, the four categories are:

Sales revenue non-managed properties

Leasing revenue non-managed properties

Sales revenue managed properties

Leasing revenue managed properties

The purpose of the algorithm is to use the historical data for the period 1 January 2016 to 30 June 2016 as set out in the  “input data” sheet  to provide a six months  forecast for the information defined in “Output report” sheet.   The next step is to forecast data for a twelve month period using the historical information for the previous twelve month.  Historical data for a twelve months period is required to achieve this.

Forecast data will be compared to actual data, to identifying any additional parameters which should be included in the algorithm to provide a more accurate forecast.    

 

Input Data 

Targets Pipeline 3 – are sale/lease targets which have been identified and could potentially move to Targets Pipeline 2 within 30 days.

Targets Pipeline 2 – are sale/lease targets where further progress has been made with the client and could potentially move to Targets Pipeline 1 within 90 days.

Targets Pipeline 1 – are sale/lease targets were we could potentially be requested by the client to prepare a submission to sell or lease within a 90 day period.

Submissions – a request to prepare a sale/lease submission for the client, which if accepted translates to an appointment to sell/lease a property.

Appointment – instruction from the client to sell/lease a property

Marketing Spend – advertising cost incurred by the client to sell/lease the property

Agency Work In Progress – estimated commission from the sale/lease appointments  

Property management Work In Progress – estimated commission from the sale/lease appointments of managed properties

Operator number of years’ experience

Probables – once negotiations commence for a sale/lease of a property estimated commission is tracked

Transaction (Revenue) – Sale/lease of a property has been finalised and commission becomes payable to GormanKelly for completing the transaction

The above information is available by number and $ value for each of the six Sales and Leasing Operators at the end of each month for a six month period.   

Algorithm

The algorithm is to forecast all the information for the next six month period as set out in the Output report sheet, based on the historical information in the Input data sheet for the previous six months.  

Output Reports

Report to include forecast of the monthly data for a six month period as set out in the “Output report” sheet.

 

  

 

 

Who We Are: 

We are an e-commerce company based in Los Angeles, California. We sell various scented products (candles, bath bombs and beads) to customers throughout the U.S. Our sales are generated primarily through three (3) channels: (i) paid advertising on platforms such as Facebook, Google, Yahoo and Pinterest, (ii) email marketing and (iii) our subscription program which offers a candle each month and certain other perks called the VIP Club.

What We Need:

We are looking data scientists to help us better understand the customer data we possess and how certain dimensions and variables affect the likelihood that our customers will purchase from us again. Specifically, we want the following:

1. A multidimensional lifetime value database broken down by time intervals (1 week, 3 weeks, 1 month, 3 months, 6 months, 9 months) after the initial order and filtered through the following dimensions:

• initial order size
• time between order and shipping label creation
• time between shipping label creation and shipment
• time between send and delivery
• location, time of day order placed
• traffic source from which order generated
• offer/deal for initial order
• city and state where the customer lives
• average email opens before second purchase
• Month of year

We would like to run each of our existing products through this model and would like to understand how candles (our first product) differ from bath bombs (our newest product) in the above respects.  We want you to create a data pipeline that will ingest all of our old data into a format incorporating the above dimensions that is also able to ingest all of our new data. 

2. A lifetime value analysis of our customers that purchased the VIP Club membership as compared to the customers that did not purchase the VIP Club membership.

• The effect that the device used by the customer to purchase (desktop, iPad, mobile) has on LTV.

3. Lifetime value analysis of customers that did not leave reviews as compared to customers that did leave reviews. 

What We Have

Approximately 600,000 sales records.Email open and click-through rates tracked on Klaviyo.

Email open and click-through rates tracked on Klaviyo

Old data format:  multiple CSVs, JSON files keyed by email.New data:

New data:  segment.com raw data files, data warehouse. 

Goal

Using the data, we would like to be able to do predictive analysis on our customers so that we can know, based upon their behavior and characteristics, how likely they are to purchase again.