{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"from IPython.display import HTML\nimport time\n\nhandle = display(HTML(\"\"\"👌\"\"\"), display_id='html_marquee1')\ntime.sleep(2)\nhandle = display(HTML(\"\"\"~ “A year spent in artificial intelligence is enough to make one believe in God.” — Alan Perlis\"\"\"), display_id='html_marquee1', update=True)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2023-06-30T09:31:39.159651Z","iopub.execute_input":"2023-06-30T09:31:39.160057Z","iopub.status.idle":"2023-06-30T09:31:41.199790Z","shell.execute_reply.started":"2023-06-30T09:31:39.160020Z","shell.execute_reply":"2023-06-30T09:31:41.198697Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"#
Executive Summary
\n\n
đź“Ś Purpose: This notebook is intended to \n
\n\nForbes AI50 List reflects the most tangible AI companies in Western world (USA and its alies). Forbes experts that collate it select the most trending companies there. \n\nThe key insgiths from the data in n Forbse AI 50 lists for 2022 and 2023 are summarized in the list below\n\n
\n \n
","metadata":{}},{"cell_type":"code","source":"import pandas as pd\nimport numpy as np\n\nimport matplotlib.pyplot as plt\nimport matplotlib.cm as cm\nimport seaborn as sns\n\nimport plotly.graph_objects as go\nfrom plotly.subplots import make_subplots\nimport plotly.express as px\nimport plotly.offline","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2023-06-30T09:31:41.202130Z","iopub.execute_input":"2023-06-30T09:31:41.202543Z","iopub.status.idle":"2023-06-30T09:31:43.521715Z","shell.execute_reply.started":"2023-06-30T09:31:41.202504Z","shell.execute_reply":"2023-06-30T09:31:43.520039Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def funding_to_numeric(financial_string):\n res = 0\n x = financial_string.replace('$', '')\n tokens = x.split(' ')\n num_val = float(tokens[0])\n multiplier = 0\n if tokens[1] == 'M':\n multiplier = 1000000\n else:\n multiplier = 1000000000\n res = int(num_val * multiplier)\n return res\n\ndef is_generative_ai(mission):\n res = 'No'\n \n generative_ai_technologies = [\n 'Chatbot application', \n 'Video and podcast editing',\n 'Open-source AI library',\n 'Photo editing',\n 'Copyrighting software', \n 'AI image generator',\n 'AI model training tools', \n 'AI model developer',\n 'Voice chatbots',\n 'Image and video editing',\n 'Synthetic video creation',\n 'Presentation creation software',\n 'Personalized search engine', \n ]\n \n if mission in generative_ai_technologies:\n res = 'Yes'\n \n return res\n\ndef fix_industry_2022_typos(industry):\n res = industry\n if res == 'Pharmacutical':\n res = 'Pharmaceutical'\n return res\n\ndef set_industry(mission_2023):\n res = 'N/A'\n \n media_entertainment = [ \n 'Video and podcast editing', \n 'Photo editing', \n 'Personalized search engine', \n 'Image and video editing',\n 'Synthetic video creation',\n 'Presentation creation software', ]\n \n consumer_tech = ['Voice analysis software']\n \n education = ['Space simulation software',]\n \n env_energy = ['Forestry satellite data analysis',]\n \n retail = ['Cashierless retail checkout',]\n \n customer_service = ['Chatbot application', 'Voice chatbots',]\n \n emp_support = ['Automated IT support', 'Digital assistant for lawyers', \n 'Legal contract management', 'Recruiting software',]\n \n agriculture = ['Weeding tractors for farming', ]\n \n cybersecurity_missions = ['Defense intelligence software',\n 'Defense software',\n 'Email cyberattack detection',\n 'Autonomous defense software',\n 'Cyberattack detection',\n ]\n \n sales_marketing_missions = ['Market intelligence search',\n 'Sales software',\n 'Copyrighting software',\n ]\n \n ds_missions = ['Data issue detection', \n 'Data storage and analytics', 'AI model developer', 'Data labeling software', \n ]\n \n ai_infrastructure = ['AI model training tools',\n 'Open-source AI library',\n 'Developer tools for AI',\n 'Data labeling provider', \n 'Internal workplace search',\n 'AI image generator',\n 'Personalized search engine', \n ]\n \n pharma = ['Clinical trial forecasting', \n 'Drug discovery', 'Drug discovery and diagnostics',]\n \n healthcare = ['Disease detection', 'Patient risk detection',]\n \n construction = ['Construction robots']\n \n transportation = ['Autonomous trucking technology', ]\n \n if mission_2023 in cybersecurity_missions:\n res = 'Cybersecurity'\n elif mission_2023 in sales_marketing_missions:\n res = 'Sales and Marketing'\n elif mission_2023 in ds_missions:\n res = 'Data Science'\n elif mission_2023 in ai_infrastructure:\n res = 'AI Infrastructure'\n elif mission_2023 in pharma:\n res = 'Pharmaceutical'\n elif mission_2023 in healthcare:\n res = 'Healthcare'\n elif mission_2023 in construction:\n res = 'Construction'\n elif mission_2023 in transportation:\n res = 'Transportation and Logistics'\n elif mission_2023 in agriculture:\n res = 'Agriculture'\n elif mission_2023 in emp_support:\n res = 'Employee Support'\n elif mission_2023 in customer_service:\n res = 'Customer Service'\n elif mission_2023 in retail:\n res = 'Retail'\n elif mission_2023 in env_energy:\n res = 'Environment and Energy'\n elif mission_2023 in education:\n res = 'Education'\n elif mission_2023 in consumer_tech:\n res = 'Consumer Technology'\n elif mission_2023 in media_entertainment:\n res = 'Media and Entertainment'\n return res","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2023-06-30T09:31:43.524585Z","iopub.execute_input":"2023-06-30T09:31:43.525185Z","iopub.status.idle":"2023-06-30T09:31:43.551956Z","shell.execute_reply.started":"2023-06-30T09:31:43.525133Z","shell.execute_reply":"2023-06-30T09:31:43.551056Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"#
Reading and Processing Data
\n\n##
Initial Data Inspection
\n\nWe need to have a deep understanding of our data in order to gather the relevant insights.\n\nWe traditionally start by characterizing the data relatively to the number of observations, number and types of features, overall missing rate, and percentage of duplicate observations. We will do it separately for the data for 2022 and 2023, respectively.\n\nLet's look at 2022 data first.","metadata":{}},{"cell_type":"code","source":"run_locally = False\nif run_locally:\n ai50_2022_dataset_path = './AI50-2022.csv'\n ai50_2023_dataset_path = './AI50-2023.csv'\nelse:\n ai50_2022_dataset_path = '../input/forbes-ai50-2022/AI50 2022.csv'\n ai50_2023_dataset_path = '../input/forbes-ai50-2023/AI50-2023.csv'\n \ndf_2022 = pd.read_csv(ai50_2022_dataset_path)\n\ndf_2023 = pd.read_csv(ai50_2023_dataset_path)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2023-06-30T09:31:43.557171Z","iopub.execute_input":"2023-06-30T09:31:43.557656Z","iopub.status.idle":"2023-06-30T09:31:43.615549Z","shell.execute_reply.started":"2023-06-30T09:31:43.557611Z","shell.execute_reply":"2023-06-30T09:31:43.614383Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_2022.head(5)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2023-06-30T09:31:43.620767Z","iopub.execute_input":"2023-06-30T09:31:43.621413Z","iopub.status.idle":"2023-06-30T09:31:43.652222Z","shell.execute_reply.started":"2023-06-30T09:31:43.621369Z","shell.execute_reply":"2023-06-30T09:31:43.651173Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_2022.info()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2023-06-30T09:31:43.653621Z","iopub.execute_input":"2023-06-30T09:31:43.653952Z","iopub.status.idle":"2023-06-30T09:31:43.678775Z","shell.execute_reply.started":"2023-06-30T09:31:43.653924Z","shell.execute_reply":"2023-06-30T09:31:43.677992Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"As we can see, the dataset contains 5 features (columns), and there is no any missing values in it.\n\nThe description of the 2022 dataset is provided in the table below.\n\n\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Feature NameDescriptionComment
NAMECompany name 
INDUSTRYThe industry where the company operated.The analysts behind the Forbes AI50 list 2022 operated with the follwing idustry classification\n
    \n
  • Agriculture
    • \n
  • AI Infrastructure
    • \n
  • Biotech
    • \n
  • Construction
    • \n
  • Consumer Technology
    • \n
  • Customer Service
    • \n
  • Cybersecurity
    • \n
  • Data Science
    • \n
  • Employee Support
    • \n
  • Environment and Energy
    • \n
  • Education
    • \n
  • Financial Services
    • \n
  • Healthcare
    • \n
  • Media and Entertainment
    • \n
  • Pharmaceutical
    • \n
  • Retail
    • \n
  • Sales and Marketing
    • \n
  • Transportation and Logistics
    • \n
\n
FUNDINGThe amount of the investment capital raised by the company due date. 
HEADQUARTERSLocation of the corporate headquaters. 
CEOName of the company's Chief Executive Officer (CEO) 
","metadata":{}},{"cell_type":"markdown","source":"As we can see, there is a minor typo in the industry names in the 2022 list. Namely, *'Pharmacutical'* is used instead of *'Pharmaceutical'* in some cases (the correct one is used in other records though). We would like to fix this typo in the data before embarked on the analytical discoveries.","metadata":{}},{"cell_type":"code","source":"df_2022['INDUSTRY'] = df_2022['INDUSTRY'].apply(lambda x: fix_industry_2022_typos(x))","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2023-06-30T09:31:43.680247Z","iopub.execute_input":"2023-06-30T09:31:43.680571Z","iopub.status.idle":"2023-06-30T09:31:43.686111Z","shell.execute_reply.started":"2023-06-30T09:31:43.680542Z","shell.execute_reply":"2023-06-30T09:31:43.684891Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Now, let's look at the data for 2023.","metadata":{}},{"cell_type":"code","source":"df_2023.head(5)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2023-06-30T09:31:43.687729Z","iopub.execute_input":"2023-06-30T09:31:43.688102Z","iopub.status.idle":"2023-06-30T09:31:43.713314Z","shell.execute_reply.started":"2023-06-30T09:31:43.688072Z","shell.execute_reply":"2023-06-30T09:31:43.712238Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_2023.info()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2023-06-30T09:31:43.714487Z","iopub.execute_input":"2023-06-30T09:31:43.715365Z","iopub.status.idle":"2023-06-30T09:31:43.732770Z","shell.execute_reply.started":"2023-06-30T09:31:43.715333Z","shell.execute_reply":"2023-06-30T09:31:43.731499Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"As we can see, the dataset contains 7 features (columns), and there is no any missing values in it.\n\nThe description of the features in the 2023 list is provided in the table below.\n\n\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Feature NameDescriptionComment
NAMECompany name. 
MISSIONBrief description of what the company does. 
FUNDINGThe amount of the investment capital raised by the company due date. 
HEADQUARTERSLocation of the corporate headquaters. 
CEOName of the company's Chief Executive Officer (CEO). 
YEAR_FOUNDEDThe year the company was found. 
EMPLOYEESNumber of the employees in the company.Approximately, as of Apr 2023.
","metadata":{}},{"cell_type":"markdown","source":"We can also see the large fraction of 2023 features is not present in the dataset for 2022 while *INDUSTRY* feature is not provided in the dataset for 2023.\n\nSuch findings make the following implications to our analytical activitties down the road\n\n- INDUSTRY feature should be recoved in 2023 dataset, based on the values in MISSION field (see *Feature Engineering* section below)\n- Certain analytics will be only feasible for 2023 data","metadata":{}},{"cell_type":"markdown","source":"\n##
Feature Engineering
\n\nBefore we proceed with the analytics and mining the insights from the datasets, we will apply the following transformations \n- convert **'FUNDING'** column to the numeric type as it is a monetary data by its nature (in both the datasets for 2022 and 2023)\n- introduce **INDUSTRY'** feature in the AI 50 dataset for 2023 based on the company mission/description, to be able to compare and match the data between 2022 and 2023 for the trend analysis\n- introduce **GENERATIVE_AI** cat feature ('Yes'/'No') in the AI 50 dataset for 2023 to indicate if a particular company contributes to the development of Generative AI technologies\n\n
đź”… Context: The additional features will help us get additional insights on the AI industry trends in 2022-2023.\n
\n\nAt the end of the feature engineering step, we are going to review the dataset to see the new features there.","metadata":{}},{"cell_type":"code","source":"df_2023['INDUSTRY'] = df_2023['MISSION'].apply(lambda x: set_industry(x))\ndf_2023['GENERATIVE_AI'] = df_2023['MISSION'].apply(lambda x: is_generative_ai(x))\ndf_2023['FUNDING'] = df_2023['FUNDING'].apply(lambda x: funding_to_numeric(x))\ndf_2022['FUNDING '] = df_2022['FUNDING '].apply(lambda x: funding_to_numeric(x))\ndf_2022.rename(columns = {'FUNDING ':'FUNDING'}, inplace = True)\ndf_2023.head()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2023-06-30T09:31:43.737040Z","iopub.execute_input":"2023-06-30T09:31:43.737431Z","iopub.status.idle":"2023-06-30T09:31:43.768135Z","shell.execute_reply.started":"2023-06-30T09:31:43.737395Z","shell.execute_reply":"2023-06-30T09:31:43.766996Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"#
AI50 2023 Insights
\n\nFirst of all, we should indicate the companies from 5 countries are represtented in AI50 2023 list. These are\n- USA\n- Canada\n- UK\n- Israel\n- Japan\n\nLet's look at contribution of the companies from Forbse AI50 2023 List to the progress of Generative AI technologies","metadata":{}},{"cell_type":"code","source":"dfg = df_2023['GENERATIVE_AI'].value_counts().reset_index()\ndfg.columns = ['GENERATIVE_AI', 'Quantity']\nfig = px.bar(dfg, x='GENERATIVE_AI', y='Quantity', title='Number of companies contributing to Generative AI' ) \nfig.show()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2023-06-30T09:31:43.769255Z","iopub.execute_input":"2023-06-30T09:31:43.769996Z","iopub.status.idle":"2023-06-30T09:31:45.481532Z","shell.execute_reply.started":"2023-06-30T09:31:43.769936Z","shell.execute_reply":"2023-06-30T09:31:45.480492Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"We see that *26%* of the companies represennted in Forbes AI50 2023 List are involved in building Generative AI technologies. It provides yet one more confirmation to the growing interest in Generative AI across the industry.","metadata":{}},{"cell_type":"code","source":"dfg = df_2023['INDUSTRY'].value_counts().reset_index()\ndfg.columns = ['INDUSTRY', 'Quantity']\nfig = px.bar(dfg, x='INDUSTRY', y='Quantity', title='Number of Companies by Industry - 2023' ) \nfig.show()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2023-06-30T09:31:45.483121Z","iopub.execute_input":"2023-06-30T09:31:45.484158Z","iopub.status.idle":"2023-06-30T09:31:45.558750Z","shell.execute_reply.started":"2023-06-30T09:31:45.484114Z","shell.execute_reply":"2023-06-30T09:31:45.557706Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"We can see that *Data Science* and *AI Infrastructure* are the top industries by the number of companies included to the List. Three more industries are quite close to the leaders. These are\n\n- Cybersecurity\n- Sales and Marketing\n- Media and Entertainment\n\nNow let's look at distribution of the companies from Forbse AI50 2023 List by the industries and contribution to Generative AI","metadata":{}},{"cell_type":"code","source":"agg_data = df_2023[[\"INDUSTRY\", \"GENERATIVE_AI\"]].groupby([\"INDUSTRY\", \"GENERATIVE_AI\"]).size().reset_index(name=\"Count\")","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2023-06-30T09:31:45.560226Z","iopub.execute_input":"2023-06-30T09:31:45.560820Z","iopub.status.idle":"2023-06-30T09:31:45.574154Z","shell.execute_reply.started":"2023-06-30T09:31:45.560788Z","shell.execute_reply":"2023-06-30T09:31:45.573240Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# define figure element\nfig = px.sunburst(\n agg_data,\n values='Count',\n path=[\"GENERATIVE_AI\", \"INDUSTRY\"],\n title=\"Distribution of Companies by Industry and Contribution to Generative AI\",\n color=\"GENERATIVE_AI\",\n height=800,\n)\n# display the figure\nfig.show()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2023-06-30T09:31:45.575793Z","iopub.execute_input":"2023-06-30T09:31:45.576235Z","iopub.status.idle":"2023-06-30T09:31:45.709667Z","shell.execute_reply.started":"2023-06-30T09:31:45.576198Z","shell.execute_reply":"2023-06-30T09:31:45.708731Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Although Generative AI started to be a mainstream trend after the recent launch of ChatGPT, Bing Chat Assistant and other Open AI-backed technologies with the power of LLM models in Mar-Apr 2023, we can see some industry convervatism/latency in terms of nominating the inventors of Generative AI technologies in the list. Namely, we can see that\n- The number of companies from AI50 2023 list involved in Generative AI technology building is less then the companies involved in other types of AI tech (*18 vs. 32*)\n- The biggest number of companies involved in Generative AI contribute to *Data Science, Media and Entertainment, and AI Infrastructure* industries\n- The biggest number of the companies not involved in Generative AI contribute to *Cybersecurity, Data Science, and Employee Support* industries","metadata":{}},{"cell_type":"markdown","source":"##
Funding Insights (2023)
\n\nLet's look at funding of the companies listed in AI50 2023 list","metadata":{}},{"cell_type":"code","source":"fig = px.box(df_2023, y=\"FUNDING\", x=\"INDUSTRY\",\n title=\"Funding of Companies by Industry (2023)\", \n color=\"GENERATIVE_AI\", # points=\"all\",\n hover_data=df_2023.columns)\n\n# Update visual layout\nfig.update_layout(\n showlegend=True,\n width=800,\n height=600,\n autosize=False,\n margin=dict(t=25, b=0, l=5, r=5),\n template=\"plotly_white\",\n)\n\n# update font size at the axes\nfig.update_coloraxes(colorbar_tickfont_size=10)\n# Update font in the titles: Apparently subplot titles are annotations (Subplot font size is hardcoded to 16pt · Issue #985)\nfig.update_annotations(font_size=12)\n# Reduce opacity\nfig.update_traces(opacity=0.75)\n\nfig.show()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2023-06-30T09:31:45.711068Z","iopub.execute_input":"2023-06-30T09:31:45.711457Z","iopub.status.idle":"2023-06-30T09:31:46.056302Z","shell.execute_reply.started":"2023-06-30T09:31:45.711420Z","shell.execute_reply":"2023-06-30T09:31:46.055372Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"We can see that\n- *Data Science, Cybersecurity, AI Infrastructure, and Pharmaceutical* industries contain the companies with the most tangible investments, within AI50 2023 list\n- there are certain funding 'outliers', with several companies demonstrated 'outstanding' investments in their business (these are famous *OpenAI* and *Databricks* as well as *Anduril Industries* involved in Cybersecurity industry)\n- if *OpenAI* excluded, the investments to Generative AI companies generally are less for the companies operated in other AI domains\n\n
đź”… Note: I analize the success story of Databricks in my other research per Kaggle in Cloud in 2020-2021, Section 'Cloud ML: Databricks breaks the wall'\n
","metadata":{}},{"cell_type":"markdown","source":"#
AI50 2022 Insights
\n\nFirst of all, we should indicate the companies from USA only are represtented in AI50 2022 list. \n\nLet's look at contribution of the companies from Forbse AI50 2022 List to different industries","metadata":{}},{"cell_type":"code","source":"dfg = df_2022['INDUSTRY'].value_counts().reset_index()\ndfg.columns = ['INDUSTRY', 'Quantity']\nfig = px.bar(dfg, x='INDUSTRY', y='Quantity', title='Number of Companies by Industry - 2022' ) \nfig.show()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2023-06-30T09:31:46.057585Z","iopub.execute_input":"2023-06-30T09:31:46.057908Z","iopub.status.idle":"2023-06-30T09:31:46.132619Z","shell.execute_reply.started":"2023-06-30T09:31:46.057880Z","shell.execute_reply":"2023-06-30T09:31:46.131585Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"We find that\n- the most of the companies in the list operate in *Data Science* and *AI Infrastructure*\n- smalller yet still significan presence of the companies from Forbse AI50 2022 List is in *Healthcare, Pharmaceutical, and Customer Service* industries","metadata":{}},{"cell_type":"code","source":"fig = px.box(df_2022, y=\"FUNDING\", x=\"INDUSTRY\",\n title=\"Funding of Companies by Industry (2022)\", \n # points=\"all\",\n hover_data=df_2022.columns)\n\n# Update visual layout\nfig.update_layout(\n showlegend=True,\n width=800,\n height=600,\n autosize=False,\n margin=dict(t=25, b=0, l=5, r=5),\n template=\"plotly_white\",\n)\n\n# update font size at the axes\nfig.update_coloraxes(colorbar_tickfont_size=10)\n# Update font in the titles: Apparently subplot titles are annotations (Subplot font size is hardcoded to 16pt · Issue #985)\nfig.update_annotations(font_size=12)\n# Reduce opacity\nfig.update_traces(opacity=0.75)\n\nfig.show()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2023-06-30T09:31:46.134172Z","iopub.execute_input":"2023-06-30T09:31:46.134761Z","iopub.status.idle":"2023-06-30T09:31:46.249235Z","shell.execute_reply.started":"2023-06-30T09:31:46.134731Z","shell.execute_reply":"2023-06-30T09:31:46.248109Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"We can see that\n- the most fundings within the listed in AI50 2022 List received the companies that operate in *Data Science, AI Infrastructure, Transpportation and Logistics, Environment and Energy, Customer Service, and Sales and Marketing* industries\n- there are certain companies that are 'outliers' in terms of the extraodinary fundings recieved (compared to other companies in their industries listed in AI50 2022 list); these are *Databricks, Scale AI, and Komodo Health*","metadata":{}},{"cell_type":"markdown","source":"#
AI50 Industry Focus Changes in 2022-2023
\n\nNow, let's look at how the focus of experts collated AI50 Lists in 2022 and 2023 shifted in terms of industries where AI applications are used. We will consider the number of companies from a certain vertical listed in AI50 to be a measure of relative importance of AI progress in certain industries.","metadata":{}},{"cell_type":"code","source":"dfg2023 = df_2023['INDUSTRY'].value_counts().reset_index()\ndfg2023.columns = ['INDUSTRY', 'COMPANY_COUNT_2023']\n\ndfg2023[['COMPANY_COUNT_2023']] = dfg2023[['COMPANY_COUNT_2023']].applymap(np.int64)\n\ndfg2022 = df_2022['INDUSTRY'].value_counts().reset_index()\ndfg2022.columns = ['INDUSTRY', 'COMPANY_COUNT_2022']\n\nouter_merged = pd.merge(\n dfg2023, dfg2022, how=\"outer\", on=[\"INDUSTRY\"]\n)\n\nouter_merged['COMPANY_COUNT_2023'] = outer_merged['COMPANY_COUNT_2023'].fillna(0)\nouter_merged[['COMPANY_COUNT_2023']] = outer_merged[['COMPANY_COUNT_2023']].applymap(np.int64)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2023-06-30T09:31:46.250765Z","iopub.execute_input":"2023-06-30T09:31:46.251462Z","iopub.status.idle":"2023-06-30T09:31:46.272989Z","shell.execute_reply.started":"2023-06-30T09:31:46.251422Z","shell.execute_reply":"2023-06-30T09:31:46.272201Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"fig = go.Figure()\n\nfig.add_bar(x=outer_merged['INDUSTRY'],y=outer_merged['COMPANY_COUNT_2022'], hovertext=\"2022\", name=\"2022\", marker_color=\"orange\")\nfig.add_bar(x=outer_merged['INDUSTRY'],y=outer_merged['COMPANY_COUNT_2023'], hovertext=\"2023\", name=\"2023\", marker_color=\"green\")\n\n# Update visual layout\nfig.update_layout(\n showlegend=True,\n width=800,\n height=400,\n autosize=False,\n margin=dict(t=30, b=0, l=5, r=5),\n template=\"plotly_white\",\n yaxis_title=\"Number of Companies\",\n title=dict(text='AI50 Industry Focus Changes in 2022-2023', font=dict(size=20), yref='paper')\n)\n\n# update font size at the axes\nfig.update_coloraxes(colorbar_tickfont_size=10)\n# Update font in the titles: Apparently subplot titles are annotations (Subplot font size is hardcoded to 16pt · Issue #985)\nfig.update_annotations(font_size=12)\n# Reduce opacity\nfig.update_traces(opacity=0.75)\n\nfig.show()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2023-06-30T09:31:46.274351Z","iopub.execute_input":"2023-06-30T09:31:46.275490Z","iopub.status.idle":"2023-06-30T09:31:46.343244Z","shell.execute_reply.started":"2023-06-30T09:31:46.275449Z","shell.execute_reply":"2023-06-30T09:31:46.342031Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"We find that\n\n- *Data Science and AI Infrastructure* industries remain the top priorities with AI innovations (and the VC capital invested into the respective companies from such industries); moreover, *Data Science* industry got more companies listed in AI50 in 2023 vs. 2022\n- *Cybersecurity, Sales and Marketing, Media and Entertainment, and Employment Suppport* industries got wider representation in AI50 2023 vs. 2022\n- *Pharmaceutial, Healthcare, and Customer Service* industries got less companies listed in 2023 vs. 2022\n- *Biotech and Financial Services* totally disappeared from the AI50 list in 2023","metadata":{}},{"cell_type":"markdown","source":"#
Funding Changes in Individual companies in 2022-2023
\n\nWe can see *10* companies from Forbse AI50 2022 list to participate in 2023 list as well. We are going to see how their funding was changed in between the time of filing both lists. ","metadata":{}},{"cell_type":"code","source":"df_2023_subset = df_2023[['NAME', 'INDUSTRY', 'FUNDING']]\ndf_2022_subset = df_2022[['NAME', 'FUNDING']]\ndf_2023_subset.rename(columns = {'FUNDING':'FUNDING_AS_OF_APR_2023'}, inplace = True)\ndf_2022_subset.rename(columns = {'FUNDING':'FUNDING_AS_OF_APR_2022'}, inplace = True)\n\n# calculate the fundings changes during the last year\ndf = df_2023_subset.merge(df_2022_subset, on='NAME')\ndf['FUNDING_CHANGES'] = df['FUNDING_AS_OF_APR_2023'] - df['FUNDING_AS_OF_APR_2022']\ndf","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2023-06-30T09:31:46.344889Z","iopub.execute_input":"2023-06-30T09:31:46.345433Z","iopub.status.idle":"2023-06-30T09:31:46.371775Z","shell.execute_reply.started":"2023-06-30T09:31:46.345403Z","shell.execute_reply":"2023-06-30T09:31:46.370280Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"We can see that\n- there are ten companies that represented in both AI50 2022 and 2023 lists, and therefore we can see if they raised funds recently (between Apr 2022 and Apr 2023)\n- the most remarkable recent capital raise happened to *Abnoral Security* (*Cybersecurity*) that raised USD 210 M recently\n- the most of other companies that raised the additional capital recently are involved in *Data Science* and *AI Infrastructure* industries\n- *Waabi* from *Transportation and Logistics* recently raised USD 1 M (the smallest amount within the listed companies)\n- some of the companies faced the capital restructuring that indicated by decrease in the corporate capital between 2022 and 2023","metadata":{}},{"cell_type":"markdown","source":"#
Industry Trends: 2022 vs. 2023
\n\nIf we compare the findings for 2022 and 2023 lists in perspective, we can draw the insights below\n\n- *Data Science* and *AI Infrastructure* stayed in focus of Forbes experts in both 2022 and 2023\n- *Cybersecurity* industry got much more traction in 2023 vs. 2022\n- In turn, *Transpportation and Logistics, Environment and Energy, Customer Service, and Sales and Marketing* got decline in terms of the number of the companies listed in 2023 vs. 2022\n- As of 2023, the listed companies from *Data Science, Cybersecurity, AI Infrastructure, and Pharmaceutical* industries raised the most capital\n- The analysis of companies that got recent investments in 2022-early 2023 also demonstrates cases of increased capital raising in *Data Science, Cybersecurity, and AI Infrastructure* industries\n- Generative AI contributors that build the infrastructure for it got significant funding; in turn, the companies that innovate with leveraging Generative AI technologies to the industrial solutions are funded on the far less scale","metadata":{}},{"cell_type":"markdown","source":"#
AI50 2023 Note From Forbes Editorial Team
\n\n
💥 Note: Artificial intelligence has captured the zeitgeist in recent months with the release of ChatGPT and a flurry of image generators. Bot-written school papers and the puffer jacket-wearing Pope have seized the public’s fascination, spreading AI’s reach far beyond the laboratories and startup offices of Silicon Valley — and in turn propelling a flurry of new businesses.

\n\nFollowers of the AI 50 will have seen this coming. Now in its fifth year, our annual list, produced in partnership with Sequoia and Meritech Capital, recognizes the most promising privately-held companies building businesses out of artificial intelligence.

\n\nCollectively, the companies on the 2023 list have received a collective USD 27.2 billion in funding. While a sizable portion, headlined by Microsoft’s USD 10 billion investment in OpenAI, was raised within the past year, many honorees have been building with AI well before the present gold rush. Mainstays like Scale AI have for years supplied the picks and shovels —and crucially, the humans — to help turn tools like ChatGPT from concept into reality. AlphaSense and Vectra AI have been in operation for more than a decade, while the largest company on the list, Databricks, employs more than 5,000 people.

\n\nMeanwhile, a flock of fledgling startups have taken advantage of the investor frenzy to assemble sizable businesses. While the rest of venture capital suffers from the market pullback, the AI sector has boomed. Adept, Anthropic and Cohere are among companies founded in the last two years to have secured hundreds of millions in investment. Midjourney and Surge AI, on the other hand, have rapidly amassed impressive customer bases without raising a cent.

\n\nThis year marks the first time we have opened AI 50 up beyond North American companies to be a global list, and Forbes received nearly 800 submissions. Applicants do not pay a fee to be considered and are judged for their business promise and technical usage of AI through a quantitative algorithm and qualitative judging panels. Companies are encouraged to share data on diversity, and our list aims to promote a more equitable startup ecosystem. Still, progress remains to be made in the industry: just 12 companies have women cofounders, five of whom serve as CEO. Eight companies have Black or Latino founders.

\n\nIn rare instances where the company did not disclose information, Forbes uses data provided by PitchBook and Crunchbase.

\n
","metadata":{}},{"cell_type":"markdown","source":"#
References
\n\n- https://www.snowflake.com/blog/snowflake-acquires-neeva-to-accelerate-search-in-the-data-cloud-through-generative-ai/\n- https://www.forbes.com/lists/ai50/","metadata":{}}]}