{"id":9149,"date":"2019-06-08T17:36:07","date_gmt":"2019-06-08T15:36:07","guid":{"rendered":"https:\/\/sourcing-force.com\/?p=9149"},"modified":"2022-11-17T11:29:34","modified_gmt":"2022-11-17T10:29:34","slug":"classifying-spend-data","status":"publish","type":"post","link":"https:\/\/sourcing-force.com\/en\/classifying-spend-data\/","title":{"rendered":"Classifying Spend Data \u2013 Do Algorithms Really Work?"},"content":{"rendered":"

[et_pb_section fb_built=”1″ module_class=”homepage blog” _builder_version=”4.16″ background_size=”contain” background_position=”bottom_center” transform_scale_tablet=”102%|102%” transform_scale_phone=”” transform_scale_last_edited=”on|phone” transform_translate_tablet=”” transform_translate_phone=”” transform_translate_last_edited=”on|tablet” transform_rotate_tablet=”” transform_rotate_phone=”” transform_rotate_last_edited=”on|desktop” transform_skew_tablet=”” transform_skew_phone=”” transform_skew_last_edited=”on|desktop” transform_origin_tablet=”” transform_origin_phone=”100%|0%” transform_origin_last_edited=”on|phone” transform_styles_last_edited=”on|phone” max_width_tablet=”” max_width_phone=”” max_width_last_edited=”on|phone” custom_padding=”50px|0|50px|0px|false|false” transform_styles_tablet=”” transform_styles_phone=”” custom_css_main_element=”background-position:center 350px !important;” global_colors_info=”{}”][et_pb_row column_structure=”1_5,3_5,1_5″ module_class=” et_pb_row_fullwidth” _builder_version=”4.16″ background_size=”initial” background_position=”top_left” background_repeat=”repeat” width=”89%” width_tablet=”80%” width_phone=”80%” width_last_edited=”on|desktop” max_width=”89%” max_width_tablet=”80%” max_width_phone=”80%” max_width_last_edited=”on|desktop” custom_padding=”0|0|28.75px|0|false|false” make_fullwidth=”on” global_colors_info=”{}”][et_pb_column type=”1_5″ _builder_version=”4.16″ custom_padding=”|||” global_colors_info=”{}” custom_padding__hover=”|||”][et_pb_image src=”https:\/\/sourcing-force.com\/wp-content\/uploads\/2019\/06\/Banner-1.png” url=”https:\/\/sourcing-force.com\/en\/the-ultimate-guide-to-spend-analysis-white-paper\/” align_tablet=”center” align_phone=”center” align_last_edited=”on|desktop” _builder_version=”4.16″ global_colors_info=”{}”][\/et_pb_image][\/et_pb_column][et_pb_column type=”3_5″ _builder_version=”4.16″ custom_padding=”|||” global_colors_info=”{}” custom_padding__hover=”|||”][et_pb_text _builder_version=”4.16″ text_font=”Abhaya Libre||||||||” text_line_height=”2.2em” background_layout=”dark” inline_fonts=”Verdana” global_colors_info=”{}” text_line_height__hover_enabled=”on” text_line_height__hover=”2.5em”]<\/p>\n

Classifying Spend Data \u2013 Do Algorithms Really Work?<\/span>
<\/strong><\/span><\/h1>\n

[\/et_pb_text][et_pb_post_title title=”off” _builder_version=”4.16″ title_font=”Trebuchet||||||||” global_colors_info=”{}”][\/et_pb_post_title][et_pb_text _builder_version=”4.17.6″ text_font=”Abhaya Libre||||||||” text_text_color=”rgba(0,0,0,0.73)” text_font_size=”15px” text_letter_spacing=”1px” text_line_height=”2.8em” background_layout=”dark” inline_fonts=”Verdana” global_colors_info=”{}” text_line_height__hover_enabled=”on” text_line_height__hover=”2.5em”]<\/p>\n

People who are new to spend analysis are trained to think that there is a magic\u00a0button to classify their spend data. If I send you my spend data you run it through your algorithms and magically my spend data will be classified perfectly for my business.<\/span><\/p>\n

The people that have been through failed spend implementations know that there will always be subjectivity in data and\u00a0an algorithm that works for one client does not work for another.\u00a0\u00a0<\/span><\/p>\n

I am not saying that algorithms do not work but you have to factor in the complexity of your business. If vendors say they have hundreds of thousands of rules, you have to ask, \u201cHow do those rules get applied to my spend data?\u201d\u00a0On average, we create anywhere from\u00a0500-2000\u00a0custom built rules\u00a0per project.<\/span><\/p>\n

[\/et_pb_text][et_pb_text _builder_version=”4.17.6″ text_font=”Abhaya Libre||||||||” text_text_color=”rgba(0,0,0,0.73)” text_font_size=”15px” text_letter_spacing=”1px” text_line_height=”2.8em” background_layout=”dark” inline_fonts=”Verdana” global_colors_info=”{}” text_line_height__hover_enabled=”on” text_line_height__hover=”2.5em”]<\/p>\n

\"\"<\/a><\/p>\n

[\/et_pb_text][et_pb_text _builder_version=”4.17.6″ text_font=”Abhaya Libre||||||||” text_text_color=”rgba(0,0,0,0.73)” text_font_size=”15px” text_letter_spacing=”1px” text_line_height=”2.8em” background_layout=”dark” inline_fonts=”Verdana” global_colors_info=”{}” text_line_height__hover_enabled=”on” text_line_height__hover=”2.5em”]<\/p>\n

Another area of concern when dealing with a classification engine built around algorithms is that change is not easy.<\/span><\/p>\n

You cannot change a standardized rule because it is just that – a standardized rule that needs to work across multiple industries classifying the data directionally correct.<\/span><\/p>\n

Directionally correct is not good enough when it comes to running initiatives.<\/span><\/p>\n

Accuracy is critical<\/strong> to gaining a clear view into your spend.<\/span><\/p>\n

Sourcing Force was recently working with a client where we ran into a dataset with high level Accounts Payable data and supplier spend that needed business specific categorizations.<\/span><\/p>\n

To give a little perspective on the client we were working with, they are a holding company with 20+ operating companies.<\/span><\/p>\n

In this client\u2019s case maybe on a portfolio by portfolio company basis algorithms would work, but doesn\u2019t that defeat the purpose of implementing an entire holding company?<\/span><\/p>\n

A prime example of classification subjectivity within classifications would be a rule for\u00a0Cintas. Cintas has a primary Industry listing of Uniform Rental & Laundry Services.<\/span><\/p>\n

So for all purposes an algorithm would classify this spend with UNSPSC<\/strong> to the code best suited to uniforms. This classification may be correct 95% of the time<\/strong> if you are implementing a manufacturing company. But let\u2019s go back to our current implementation of our holding company.<\/span><\/a><\/p>\n

[\/et_pb_text][et_pb_text _builder_version=”4.17.6″ text_font=”Abhaya Libre||||||||” text_text_color=”rgba(0,0,0,0.73)” text_font_size=”15px” text_letter_spacing=”1px” text_line_height=”2.8em” background_layout=”dark” inline_fonts=”Verdana” global_colors_info=”{}” text_line_height__hover_enabled=”on” text_line_height__hover=”2.5em”]<\/p>\n

\"\"<\/p>\n

[\/et_pb_text][et_pb_text _builder_version=”4.17.6″ text_font=”Abhaya Libre||||||||” text_text_color=”rgba(0,0,0,0.73)” text_font_size=”15px” text_letter_spacing=”1px” text_line_height=”2.8em” background_layout=”dark” inline_fonts=”Verdana” global_colors_info=”{}” text_line_height__hover_enabled=”on” text_line_height__hover=”2.5em”]<\/p>\n

Within one of the operating companies in this holding company Cintas was classified to uniforms, floor or area mats, document destruction, and one that no algorithm would ever catch, this company was buying back the paper that they were shredding to recycle into their products they are producing.<\/span><\/p>\n

Again for this project we only have AP data.<\/span><\/p>\n

<\/blockquote>\n

[\/et_pb_text][et_pb_text _builder_version=”4.17.6″ text_font=”Abhaya Libre||||||||” text_text_color=”rgba(0,0,0,0.73)” text_font_size=”15px” text_letter_spacing=”1px” text_line_height=”2.8em” background_layout=”dark” inline_fonts=”Verdana” global_colors_info=”{}” text_line_height__hover_enabled=”on” text_line_height__hover=”2.5em”]<\/p>\n

So how is it expected that a system built on algorithms is going to classify data based off a supplier name and spend amount?<\/strong><\/span><\/p>\n

<\/blockquote>\n

[\/et_pb_text][et_pb_text _builder_version=”4.17.6″ text_font=”Abhaya Libre||||||||” text_text_color=”rgba(0,0,0,0.73)” text_font_size=”15px” text_letter_spacing=”1px” text_line_height=”2.8em” background_layout=”dark” inline_fonts=”Verdana” global_colors_info=”{}” text_line_height__hover_enabled=”on” text_line_height__hover=”2.5em”]<\/p>\n

An algorithm may give you a start to where the classification is directionally correct but until you understand the client you are working with and how they buy you will never feel confident that you have accurate classifications.\u00a0 \u00a0<\/span><\/p>\n

Classification is an area where Sourcing Force stands out! With access into the Rule Builder which allows for any data field to be classified it takes the guessing out of classification and puts the confidence in it.<\/span><\/p>\n

With our functionality you have complete control of your spend!<\/span><\/p>\n

Spend Analysis the heart of spend management initiatives, shouldn\u2019t you have an accurate view of your spends?\u00a0<\/span><\/p>\n

<\/blockquote>\n

[\/et_pb_text][et_pb_text _builder_version=”4.17.6″ text_font=”Abhaya Libre||||||||” text_text_color=”rgba(0,0,0,0.73)” text_font_size=”15px” text_letter_spacing=”1px” text_line_height=”2.8em” background_layout=”dark” inline_fonts=”Verdana” global_colors_info=”{}” text_line_height__hover_enabled=”on” text_line_height__hover=”2.5em”]<\/p>\n

\"\"<\/a><\/p>\n

<\/blockquote>\n

[\/et_pb_text][\/et_pb_column][et_pb_column type=”1_5″ _builder_version=”4.16″ custom_padding=”|||” global_colors_info=”{}” custom_padding__hover=”|||”][et_pb_divider show_divider=”off” _builder_version=”4.16″ global_colors_info=”{}”][\/et_pb_divider][\/et_pb_column][\/et_pb_row][\/et_pb_section][et_pb_section fb_built=”1″ module_class=”homepage endcta quickform” _builder_version=”3.29.3″ background_image=”https:\/\/sourcing-force.com\/wp-content\/uploads\/2019\/09\/Artboard-21-min.jpg” transform_translate=”0px|95px” custom_margin=”-100px||||false|false” custom_padding=”0px||62px||false|false” global_module=”4803″ locked=”off” global_colors_info=”{}”][et_pb_row _builder_version=”4.16″ background_size=”initial” background_position=”top_left” background_repeat=”repeat” global_colors_info=”{}”][et_pb_column type=”4_4″ _builder_version=”4.16″ custom_padding=”|||” global_colors_info=”{}” custom_padding__hover=”|||”][et_pb_text admin_label=”Footer CTA” module_class=”quickform” _builder_version=”4.16″ header_text_align=”center” text_orientation=”center” background_layout=”dark” global_colors_info=”{}”]<\/p>\n

Shedule a demo today<\/h3>\n

We will contact you as soon as possible<\/h4>\n

[\/et_pb_text][et_pb_button button_url=”https:\/\/sourcing-force.com\/en\/contact\/” url_new_window=”on” button_text=”Schedule Demo” button_alignment=”center” _builder_version=”4.16″ global_colors_info=”{}”][\/et_pb_button][et_pb_code _builder_version=”4.16″ text_orientation=”left” global_colors_info=”{}”]