{"id":1937,"date":"2019-09-09T02:49:32","date_gmt":"2019-09-09T02:49:32","guid":{"rendered":"http:\/\/kusuaks7\/?p=1542"},"modified":"2024-04-17T12:06:41","modified_gmt":"2024-04-17T12:06:41","slug":"how-data-science-teams-can-be-more-methodical-part-1","status":"publish","type":"post","link":"https:\/\/www.experfy.com\/blog\/bigdata-cloud\/how-data-science-teams-can-be-more-methodical-part-1\/","title":{"rendered":"How Data Science teams can be more methodical \u2013 Part 1"},"content":{"rendered":"\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tAnother tip for success with your\u00a0Data Science team<\/a>\u00a0is to be more methodical.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tBy this, I mean to establish and use a consistent methodology, process or workflow. This will enable repeatable results, simpler collaboration &\u00a0knowledge transfer<\/a>. If it is a well\u2013designed methodology, it should also ensure appropriate\u00a0QA<\/a>\u00a0stages and reduce the cost of rework.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tA few different influences have had me thinking about this topic recently.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

Lack of methodical approach \u2013 a common problem<\/h2><\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tOver recent years, within academic research, there has been\u00a0a plea for better reproducibility of results<\/a>. Time and time again exciting studies have failed to have their findings reproduced, with the inevitable call for more rigour.\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tMy own work training\u00a0Data Science teams<\/a>\u00a0and coaching their leaders has also revealed this problem. Too many teams, sometimes under the smokescreen of being \u201cagile<\/a><\/em>\u201d or \u201cinnovative<\/a><\/em>\u201c, are basically making it up as they go along. Different team members using different work processes and so hindering both consistent quality & collaboration.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tThirdly, I have recently started as a guest lecturer at my local university, helping out on their\u00a0MSc Data Science programme<\/a>. The module I am teaching includes a focus on Data Science methodologies. Researching this has reminded me how little progress has been made.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tThat comment relates to my memory of Data Mining prior to what is now called the \u201cAI Winter<\/a>\u201c. Back in the 1990s, I was working in R&D building Neural Network, Genetic Algorithm & Fuzzy Logic models. I then went on to create the\u00a0Analytics\u00a0and neophyte Data Science teams. Even then it was clear that we needed to improve processes. There was a lack of\u00a0common standards<\/a>\u00a0that hindered our progress.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

A few of the more popular Data Science methodologies<\/h2><\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tSo, rather than gripe (or worse still \u201cpoint fingers<\/em>\u201c), let me try and help by highlighting what does exist in the way of\u00a0Data Science<\/a>\u00a0methodologies. Back in the 1990s others helped me by pointing out emerging standards in Data Mining, so let me try and pass on the favour.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tFirst a caveat. I am not a\u00a0Data Scientist<\/a>, although I have worked around them and managed them for years. So, please feel free to share any\u00a0pitfalls<\/a>\u00a0in what I am sharing or gaps in my knowledge. This post will not be comprehensive, I just hope it helps prompt\u00a0Data Science leader<\/a>s to think more about this need for their teams.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

1) CRISP-DM<\/h3><\/h3>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\"\"\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tLet me start with a methodology that is as old as my experience. The CRoss-Industry Standard Process for Data Mining (CRISP-DM) was the standard that emerged as the most popular back in the 1990s. It helped bring more consistency and methodical approach to what was an iterative exploration.\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tAlthough I knew it was still used be some\u00a0Data Science teams<\/a>, I was surprised to find that polls still showed it to be the most popular method. It certainly is still relevant for Data Science, but the dominance showed in this poll from KD Nuggets surprised me:\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tFortunately, this methodology has been around long enough to have more supporting material available than just the most familiar diagram. Nicole Leaper\u2019s excellent\u00a0EXDE design blog<\/a>\u00a0shares this useful visual summary:\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

2) KDD<\/h3><\/h3>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\"\"\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tDespite my greater awareness of CRISP-DM at the time, apparently, this KDD process preceded it. It was published in a copy of the American Association for\u00a0AI<\/a>\u00a0in 1996. Once again this was grounded in the experience of Data Mining practice.\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tIt had the advantage of more clearly calling out the need for not just preprocessing of data nut normally transformation before \u201cdata mining<\/em>\u201d to discover patterns. Visually it was also simpler to understand, whilst retaining the feedback arrows that CRISP-DM used to indicate the cycles prompted by discovery.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tAs with CRISP-DM, if you replace the term Data Mining with Modelling or Algorithm Selection & Usage \u2013 this method still works for\u00a0Data Science<\/a>. I can see why it also retains its place as the 5th most popular Data Science methodology in use today.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tThe original paper is also still worth reading to understand the nuances of this method:\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

3) SEMMA<\/h3><\/h3>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\"\"\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tLastly, it would be remiss of me not to mention the methodology pioneered by what used to be the most dominant statistical modelling software. Around the time that these Data Mining methods were being pioneered, large corporations were committing to SAS Software.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tIt is easy to criticise large (even privately owned) software companies, especially when they become overly dominant in their markets. Microsoft & IBM have been there in the past. Think Apple, Amazon & Google now. However, just as we tend to now acknowledge how IBM & Microsoft advanced IT usage over decades, perhaps we can also look more kindly on SAS. It has invested huge amounts in R&D over the years.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tOne of the fruits of their labours in this regard in a methodology and associated processes called\u00a0SEMMA<\/a>. It was supported by SAS training and exhausting levels of documentation. But, it did bring to a generation of SAS coders who were also statistical models (surely nascent Data Scientists) a method for the software they used day to day.\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tIf only for that reason, it is still worth today\u2019s\u00a0R<\/a>\u00a0&\u00a0Python<\/a>\u00a0coders checking this out. A chance to think through how the same rigour could be applied on their data platforms and via a wider range of software tools & languages. SAS still publishes useful detail on this method:\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

Do you still use one of these 3 older methods to be methodical?<\/h2>\n<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tThere is no shame in it if you do. Another way to phrase that would be \u201ctried and tested<\/em>\u201c. If that\u00a0KD Nuggets poll from 2017<\/a>\u00a0is still valid, it sounds like most\u00a0Data Science teams<\/a>\u00a0do still use one of these methods. I\u2019d certainly advocate that over the Wild West of lacking a methodical common process.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tHowever, as Dylan\u2019s often quoted song goes, \u201ctimes they are a\u2019 changing.<\/em>\u201d Even that KDD poll identified that the 2nd most popular methodology used by\u00a0Data Science teams<\/a>\u00a0was one developed \u2018in house<\/em>\u2018. In the second of this\u00a0series\u00a0I will share some of those more recent options.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tThat post will include an example from a technology company, a management consultant and others. Before then, I\u2019d love to hear your view of this post. Do you also see a need to have more methodical processes in\u00a0Data Science teams<\/a>? Does your team have the common methodology, process or workflow it needs?\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<\/div>\n\t\t","protected":false},"excerpt":{"rendered":"

Another tip for success with your\u00a0Data Science team\u00a0is to be more methodical.By this, I mean to establish and use a consistent methodology, process or workflow. This will enable repeatable results, simpler collaboration &\u00a0knowledge transfer. If it is a well\u2013designed methodology, it should also ensure appropriate\u00a0QA\u00a0stages and reduce the cost of rework.A few different influences have<\/p>\n","protected":false},"author":639,"featured_media":3870,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"content-type":"","footnotes":""},"categories":[187],"tags":[94],"ppma_author":[3364],"class_list":["post-1937","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-bigdata-cloud","tag-data-science"],"authors":[{"term_id":3364,"user_id":639,"is_guest":0,"slug":"paul-laughlin","display_name":"Paul Laughlin","avatar_url":"https:\/\/secure.gravatar.com\/avatar\/?s=96&d=mm&r=g","user_url":"","last_name":"Laughlin","first_name":"Paul","job_title":"","description":"Paul Laughlin is Founder and Managing Director at Laughlin Consultancy Ltd<\/a> that helps companies generate sustainable value from their customer insight, His speaking focuses on topics including Customer Insight, Leadership, Data, Analytics, Data Science, and Research & Database Marketing. Follow Customer Insight blog<\/a>."}],"_links":{"self":[{"href":"https:\/\/www.experfy.com\/blog\/wp-json\/wp\/v2\/posts\/1937","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.experfy.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.experfy.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.experfy.com\/blog\/wp-json\/wp\/v2\/users\/639"}],"replies":[{"embeddable":true,"href":"https:\/\/www.experfy.com\/blog\/wp-json\/wp\/v2\/comments?post=1937"}],"version-history":[{"count":5,"href":"https:\/\/www.experfy.com\/blog\/wp-json\/wp\/v2\/posts\/1937\/revisions"}],"predecessor-version":[{"id":36645,"href":"https:\/\/www.experfy.com\/blog\/wp-json\/wp\/v2\/posts\/1937\/revisions\/36645"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.experfy.com\/blog\/wp-json\/wp\/v2\/media\/3870"}],"wp:attachment":[{"href":"https:\/\/www.experfy.com\/blog\/wp-json\/wp\/v2\/media?parent=1937"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.experfy.com\/blog\/wp-json\/wp\/v2\/categories?post=1937"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.experfy.com\/blog\/wp-json\/wp\/v2\/tags?post=1937"},{"taxonomy":"author","embeddable":true,"href":"https:\/\/www.experfy.com\/blog\/wp-json\/wp\/v2\/ppma_author?post=1937"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}