Which Machine Learning to use? A #cheatsheet

In current teams driving data science, there has been an on-slot of discussions around which machine learning method to use and which algorithms perform optimally for which solutions.

There are several dependencies to make that decision. Some are primarily linked to:
1. Type of data: such as quantity, quality and varsity in data.
2. Resources for the task
3. Expected time for the task
4. Expectation from the data
etc.

Our friends at SAS has put together a great cheet sheet that could work as a great starting point.

Chart picked from: SAS Blog

Originally Posted at: Which Machine Learning to use? A #cheatsheet

Data And Analytics Collaboration Is A Win-Win-Win For Manufacturers, Retailers And Consumers

Collaboration between consumer packaged goods (CPG) manufacturers and retailers is more important than ever. Why? It’s because manufacturers struggle with fading brand loyalty from price sensitive consumers who are increasingly switching to private label, niche or locally-produced products. And at the same time, retailers face two major challenges of their own: showrooming—when shoppers come into the store to browse before buying online—and pressures from aggressive online retailers.

To best counter these and other issues, manufacturers and retailers need to engage as partners. Through data and analytic collaboration, they can establish a critical connection that enables them to work together to co-create differentiated in-store experiences that deliver mutual benefits.

Everybody Wins

Consumers used to get product information from advertisements and by talking to salespeople in brick-and-mortar stores. Today, shoppers aggressively research and compare products before setting foot inside a store. Or even while in the store by looking across competitive retailer outlets on their smartphones and tablets. Due to the mobile revolution, prices, product variations and reviews are more available and easier to compare than ever.
This showrooming trend can result in lost customers and lost revenues. It also renders traditional approaches to collaboration between manufacturers and retailers ineffective. Making decisions based on historical sales data is no longer sufficient. Driving category growth is increasingly about serving the right information to the shopper at the right time to support a purchase decision.

What’s needed is cooperation along with analysis of integrated data to deliver actionable insights that enable better brand, product, packaging, supply chain and business planning decisions; and to power shopper marketing programs in-store and online. This approach benefits not only manufacturers and retailers, but also consumers who enjoy the advantages of shopper reward and loyalty programs.

The Winning Road

With many shopping decisions being made outside the store environment, there is an increased priority placed on understanding and influencing shopper behavior at many points along the path to purchase. Mobile, social networks, Web and email channels are the new media used every day by marketers to target content and offers that drive purchase activity. One-to-one relationships are becoming the new currency upon which the most valued brands are based, while creating unique shopper experiences has come to define retail excellence.

Leading CPG companies have differentiated themselves by executing laser-focused consumer connection strategies based on data analytics. A variety of data-driven decisions, from assortment and inventory planning through pricing and trade promotion, all affect shopper purchase outcomes.

Based on integrated and detailed data from sources such as the retailer’s point-of-sale system, loyalty programs, syndicated sources and data aggregators, analytics allows CPG companies to become more relevant to their consumers by meeting their needs, earning their loyalty and building relationships. In short, advanced analytics separate successful retail-manufacturer partnerships from those that aren’t.
Focus On Demand

Maintaining an efficient distribution and inventory process is critical to maximizing financial performance and meeting buyers’ expectations. Sharing shopper data and insights supports concepts such as collaborative demand forecasting, dynamic replenishment and vendor-managed inventory.

Price, promotion and shelf placement are critical areas that drive collaboration, but the efforts are often based on summary-level and infrequently updated data. To effectively move the needle in managing a category at the shelf, organizations must have a strong analytics foundation. Armed with better insights, category managers, store operations leaders, merchandise planners and allocation decision-makers can optimize the factors that influence sales performance of products in specific categories, geographies and stores.

Value In Data-Driven Collaboration

CPG manufacturer and retail business executives recognize the value of fact-based decision making enabled by integrated data and real-time analytics. Data-driven collaboration establishes a beneficial connection that allows both sides to achieve common objectives, including increased product sales, growth in revenue and brand loyalty.

Gib Bassett is the global program director for Consumer Goods at Teradata.

Justin Honaman is a Partner with Teradata and leads the National Consumer Goods Industry Consulting practice.

This story originally appeared in the Q2 2014 issue of Teradata Magazine.

Originally posted via “Data And Analytics Collaboration Is A Win-Win-Win For Manufacturers, Retailers And Consumers”.

Originally Posted at: Data And Analytics Collaboration Is A Win-Win-Win For Manufacturers, Retailers And Consumers